© 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. 5415
    Prev
    Next
    INDEX
    Explanations

    exact or precise instances or descriptions

    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
    651
    +0.24
    0.8%
    223
    +0.17
    0.5%
    126
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.24
    0.05
    151
    +0.17
    0.05
    43
    +0.15
    0.04
    Negative Logits
    ker
    -1.25
    asta
    -1.09
    olyn
    -1.06
    kers
    -1.03
    isson
    -1.00
    roe
    -0.99
     Tome
    -0.98
    cffff
    -0.97
     Mushroom
    -0.97
    oly
    -0.97
    POSITIVE LOGITS
     aligned
    1.05
    ãĤ¨
    1.04
     wrong
    1.01
     calibrated
    0.98
     suited
    0.96
     tuned
    0.95
     opposite
    0.94
     matched
    0.93
     align
    0.93
     positioned
    0.92
    Activations Density 0.432%

    No Known Activations