Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13271
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations posed as rhetorical questions

    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
    +0.28
    1.3%
    393
    +0.10
    0.5%
    406
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.29
    687
    +0.10
    0.10
    551
    +0.10
    0.10
    Negative Logits
    photo
    -0.68
    ixel
    -0.67
    operated
    -0.64
    ELD
    -0.61
    vor
    -0.61
    apeshifter
    -0.60
    Runner
    -0.59
    iHUD
    -0.59
    wordpress
    -0.59
    orge
    -0.59
    POSITIVE LOGITS
    ?]
    0.82
     invoke
    0.74
     emulate
    0.72
     intervene
    0.70
     concede
    0.70
     succumb
    0.69
     indulge
    0.68
    itia
    0.68
    ucc
    0.67
     elevate
    0.67
    Activations Density 12.575%

    No Known Activations