© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4206
    Prev
    Next
    INDEX
    Explanations

    ids of a sentence where someone is aiming to accomplish something

    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
    109
    +0.05
    0.5%
    319
    +0.05
    0.5%
    208
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.05
    0.07
    107
    +0.05
    0.04
    759
    +0.05
    0.07
    Negative Logits
     Flavoring
    -0.37
     ageing
    -0.31
     aging
    -0.30
     acidic
    -0.28
     Dou
    -0.28
     Volcano
    -0.27
    eding
    -0.27
     Admir
    -0.26
     Tornado
    -0.26
    umbered
    -0.26
    POSITIVE LOGITS
    owment
    0.46
    angering
    0.42
    orses
    0.33
    ocrin
    0.33
    game
    0.33
    omorphic
    0.32
    ocrine
    0.32
     justifies
    0.32
    games
    0.31
    urances
    0.30
    Activations Density 5.631%

    No Known Activations