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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32234
    Prev
    Next
    INDEX
    Explanations

    phrases related to adherence or commitment to a particular course of action or plan

    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
    447
    +0.15
    0.6%
    274
    +0.15
    0.6%
    438
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.15
    0.10
    526
    +0.15
    -0.05
    438
    +0.14
    0.07
    Negative Logits
     unfocusedRange
    -0.78
    inators
    -0.77
    ryption
    -0.74
     guiIcon
    -0.74
    earch
    -0.73
    ennial
    -0.72
    andals
    -0.72
    eur
    -0.72
    OTO
    -0.72
    çļĦ
    -0.71
    POSITIVE LOGITS
     plaster
    1.15
     sticks
    0.98
     stick
    0.95
     onto
    0.93
     blender
    0.90
    holder
    0.84
    holders
    0.84
     faithfully
    0.83
    tails
    0.83
    river
    0.82
    Activations Density 7.036%

    No Known Activations