© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35049
    Prev
    Next
    INDEX
    Explanations

    verbs related to physically holding or grasping onto something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve maintaining or holding onto something, either physically or metaphorically

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    587
    +0.13
    0.6%
    447
    +0.13
    0.6%
    83
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.33
    362
    +0.13
    0.18
    608
    +0.10
    0.24
    Negative Logits
    anooga
    -0.87
    enegger
    -0.78
     guiActiveUn
    -0.75
    ²¾
    -0.74
    omsky
    -0.74
    umenthal
    -0.73
    eller
    -0.72
    lehem
    -0.71
    etheus
    -0.71
    aturdays
    -0.70
    POSITIVE LOGITS
     cling
    0.86
     reins
    0.76
     hold
    0.70
     scraps
    0.69
     intact
    0.69
     Remain
    0.68
    hold
    0.68
     retain
    0.67
     residual
    0.67
     Hold
    0.67
    Activations Density 13.361%

    No Known Activations