© 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. 5302
    Prev
    Next
    INDEX
    Explanations

    information related to software development and tools used in programming

    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
    393
    +0.26
    1.0%
    566
    +0.16
    0.6%
    167
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.26
    0.13
    169
    +0.16
    0.11
    354
    +0.14
    0.10
    Negative Logits
     Gibbs
    -0.82
     Samoa
    -0.82
    Kat
    -0.80
    ice
    -0.80
     Katie
    -0.79
    nutrition
    -0.78
    icy
    -0.77
     Dimension
    -0.77
    math
    -0.77
     Arkham
    -0.76
    POSITIVE LOGITS
    're
    1.90
    've
    1.66
    'll
    1.51
     guys
    1.35
    'd
    1.26
     encount
    1.18
     know
    1.15
     owe
    1.13
     want
    1.10
     intend
    1.10
    Activations Density 1.221%

    No Known Activations