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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40325
    Prev
    Next
    INDEX
    Explanations

    mentions of geological measurements like lengths in millimeters

    oai_token-act-pair · gpt-3.5-turbo
    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
    420
    +0.12
    0.6%
    746
    +0.09
    0.5%
    383
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.20
    326
    +0.09
    0.21
    501
    +0.09
    0.09
    Negative Logits
    cloth
    -0.69
    caps
    -0.61
    uctor
    -0.57
     reserve
    -0.56
    idential
    -0.55
    selection
    -0.54
     protective
    -0.53
     vain
    -0.53
    usal
    -0.52
     prevail
    -0.52
    POSITIVE LOGITS
    allic
    1.04
    rics
    1.00
    rium
    0.94
    rial
    0.91
    imet
    0.82
    atars
    0.82
    reon
    0.80
    abolic
    0.80
    een
    0.80
    eor
    0.77
    Activations Density 7.543%

    No Known Activations