© 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. 1351
    Prev
    Next
    INDEX
    Explanations

    names related to specific individuals in the context of various events or situations

    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
    285
    +0.18
    0.5%
    60
    +0.17
    0.5%
    433
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.18
    0.09
    659
    +0.17
    0.08
    326
    +0.16
    0.10
    Negative Logits
    schild
    -1.34
    stretched
    -1.14
    é¾įå¥ij士
    -1.05
    enegger
    -1.04
    orage
    -1.04
    minded
    -1.03
    ãĥ¼ãĥĨãĤ£
    -1.01
    footed
    -1.01
     EDITION
    -1.00
     GOODMAN
    -1.00
    POSITIVE LOGITS
    anut
    1.74
    asant
    1.50
    anuts
    1.44
    gging
    1.43
    pperc
    1.42
    oples
    1.41
    eper
    1.34
    ggie
    1.34
    eking
    1.33
    ggy
    1.33
    Activations Density 2.369%

    No Known Activations