© 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. 13656
    Prev
    Next
    INDEX
    Explanations

    references to reasons or justifications for actions or events

    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
    608
    +0.14
    0.5%
    591
    +0.13
    0.5%
    195
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    591
    +0.14
    0.03
    272
    +0.13
    0.03
    737
    +0.13
    0.03
    Negative Logits
     needle
    -1.02
     Carbuncle
    -1.00
     Tsukuyomi
    -0.92
    thus
    -0.80
    yss
    -0.78
     IPM
    -0.77
     needles
    -0.77
     blades
    -0.76
    eals
    -0.76
    bilt
    -0.76
    POSITIVE LOGITS
    abl
    1.19
     why
    1.14
    ="#
    0.98
    reason
    0.94
    rand
    0.93
    rid
    0.92
     explaining
    0.88
    TextColor
    0.85
    stadt
    0.85
    why
    0.84
    Activations Density 0.167%

    No Known Activations