© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14169
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics and player details

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    326
    +0.19
    0.6%
    310
    +0.19
    0.6%
    35
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.19
    0.12
    260
    +0.19
    0.12
    693
    +0.17
    0.11
    Negative Logits
    idable
    -1.06
    deen
    -1.03
    agents
    -1.02
    claimer
    -1.00
    igm
    -0.93
    lucent
    -0.93
    gran
    -0.93
    Reviewed
    -0.93
    eus
    -0.92
    ellation
    -0.91
    POSITIVE LOGITS
     consecutive
    1.32
     percent
    1.27
    ½
    1.22
     minutes
    1.22
    %,
    1.20
    %
    1.19
     Minutes
    1.19
     mph
    1.15
    rd
    1.15
    cm
    1.13
    Activations Density 1.243%

    No Known Activations