© 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. 13826
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, places, or events from the world of sports

    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
    728
    +0.11
    0.6%
    739
    +0.10
    0.5%
    351
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.24
    288
    +0.10
    0.25
    659
    +0.10
    0.10
    Negative Logits
    daq
    -0.83
    culosis
    -0.71
    lasses
    -0.70
    olitan
    -0.69
    ivities
    -0.69
    jac
    -0.68
    flix
    -0.68
    ropri
    -0.67
    gart
    -0.67
    nings
    -0.67
    POSITIVE LOGITS
     Hammond
    0.66
     Beir
    0.59
     Kramer
    0.59
     Pend
    0.58
     Melvin
    0.56
     Petra
    0.55
     Manson
    0.55
     Drivers
    0.54
     Kah
    0.54
     KR
    0.53
    Activations Density 8.417%

    No Known Activations