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

    Neuronpedia

    APICircuit 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. 13453
    Prev
    Next
    INDEX
    Explanations

    instances where there is a lack of something, specifically focusing on the word "enough"

    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
    +0.17
    0.7%
    50
    +0.12
    0.5%
    375
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.30
    442
    +0.12
    0.16
    6
    +0.12
    0.20
    Negative Logits
    amon
    -0.88
    ista
    -0.79
    folk
    -0.78
    eson
    -0.78
    inarily
    -0.77
    mist
    -0.75
    occ
    -0.75
    eer
    -0.75
    gob
    -0.74
    inav
    -0.71
    POSITIVE LOGITS
    natureconservancy
    0.90
     calories
    0.79
     bedrooms
    0.79
    HUD
    0.77
    inventoryQuantity
    0.77
    GoldMagikarp
    0.74
     Centauri
    0.70
     times
    0.69
     ILCS
    0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.68
    Activations Density 6.971%

    No Known Activations