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. 34689
    Prev
    Next
    INDEX
    Explanations

    words related to sudden events or changes

    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%
    718
    +0.13
    0.6%
    422
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.28
    -0.07
    718
    +0.13
    0.13
    393
    +0.11
    0.20
    Negative Logits
    tein
    -0.88
    atu
    -0.73
    tips
    -0.69
    rf
    -0.69
    ippi
    -0.68
    fman
    -0.68
    artisan
    -0.67
    matically
    -0.64
    orem
    -0.64
    rogens
    -0.64
    POSITIVE LOGITS
     vanish
    0.90
    aneously
    0.89
     burst
    0.86
     disappear
    0.86
     suddenly
    0.85
     magically
    0.78
     silenced
    0.77
    forth
    0.77
     snatched
    0.76
     disappears
    0.74
    Activations Density 7.427%

    No Known Activations