© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 40023
    Prev
    Next
    INDEX
    Explanations

    phrases related to combat sports, specifically mixed martial arts (MMA) and Ultimate Fighting Championship (UFC) events and outcomes

    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
    +0.18
    0.7%
    45
    +0.13
    0.5%
    268
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.18
    0.07
    627
    +0.13
    0.06
    590
    +0.12
    0.06
    Negative Logits
     Helpful
    -1.03
    natureconservancy
    -0.97
    Newsletter
    -0.97
     UNCLASSIFIED
    -0.95
    ulhu
    -0.87
     Gutenberg
    -0.87
    berra
    -0.86
    aceae
    -0.86
    sonian
    -0.84
    PsyNetMessage
    -0.83
    POSITIVE LOGITS
     rematch
    1.34
     MMA
    1.31
     bout
    1.17
     undefeated
    1.12
     stopp
    1.10
     wrestlers
    1.10
     matchup
    1.09
     matchups
    1.09
    UFC
    1.09
     UFC
    1.08
    Activations Density 15.616%

    No Known Activations