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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 45694
    Prev
    Next
    INDEX
    Explanations

    statements or opinions preceded by "That said," or "That said," followed by a brief commentary or additional information

    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
    +0.22
    1.3%
    709
    +0.08
    0.5%
    274
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.22
    0.07
    679
    +0.08
    0.17
    14
    +0.08
    0.04
    Negative Logits
    elled
    -0.62
    vous
    -0.52
    prus
    -0.50
    pins
    -0.49
    arded
    -0.48
    eatured
    -0.48
    cat
    -0.48
    Lat
    -0.48
    existent
    -0.47
     Roads
    -0.47
    POSITIVE LOGITS
     caveats
    0.65
    lihood
    0.59
    itivity
    0.57
     caveat
    0.54
     respectfully
    0.53
     hindsight
    0.53
     aside
    0.53
    ifference
    0.52
     anecd
    0.52
    fter
    0.51
    Activations Density 9.209%

    No Known Activations