© 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. 32898
    Prev
    Next
    INDEX
    Explanations

    tokens related to computer programming and technical documentation

    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
    88
    +0.03
    0.5%
    710
    +0.03
    0.5%
    447
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.03
    0.29
    362
    +0.03
    0.18
    393
    +0.02
    0.30
    Negative Logits
    soDeliveryDate
    -0.20
    QB
    -0.20
    rang
    -0.20
    ~~~~~~~~
    -0.19
    inks
    -0.18
    ubs
    -0.18
    uren
    -0.18
    ãĤ¼ãĤ¦ãĤ¹
    -0.18
    RED
    -0.17
    hops
    -0.17
    POSITIVE LOGITS
    slaught
    0.23
    erous
    0.22
     successive
    0.19
     average
    0.18
     behalf
    0.18
    sets
    0.16
     aggregate
    0.16
     Parade
    0.16
     exit
    0.16
     consecutive
    0.16
    Activations Density 12.250%

    No Known Activations