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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4327
    Prev
    Next
    INDEX
    Explanations

    people's names or proper nouns related to news articles or political events

    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
    0.9%
    680
    +0.10
    0.6%
    272
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.15
    0.07
    408
    +0.10
    0.17
    77
    +0.09
    0.08
    Negative Logits
    antry
    -0.60
    heit
    -0.57
    uddin
    -0.56
    isine
    -0.56
    rology
    -0.56
    enne
    -0.54
    expression
    -0.51
    someone
    -0.51
    itivity
    -0.51
    ylum
    -0.50
    POSITIVE LOGITS
     thirds
    0.81
     halves
    0.79
     paragraphs
    0.70
     generations
    0.67
     continents
    0.65
     sets
    0.64
     pairs
    0.62
     factions
    0.61
     pillars
    0.60
     brothers
    0.60
    Activations Density 12.091%

    No Known Activations