© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9113
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms, codes, and information related to computer programs

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    43
    +0.18
    0.6%
    331
    +0.14
    0.5%
    356
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.18
    0.02
    699
    +0.14
    0.02
    176
    +0.14
    0.03
    Negative Logits
    enium
    -0.99
    ĸļ
    -0.89
    onian
    -0.87
    enture
    -0.86
    ero
    -0.85
    INESS
    -0.83
    development
    -0.81
    aed
    -0.81
    ylum
    -0.79
    afety
    -0.78
    POSITIVE LOGITS
    RECT
    1.06
    Æ
    0.94
     Voy
    0.86
    Ò
    0.85
     Coul
    0.85
     Caval
    0.83
    catentry
    0.79
    oeuv
    0.79
     NAV
    0.79
     ANG
    0.78
    Activations Density 0.709%

    No Known Activations