© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to gaming, programming, sports, and medical information

    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
    151
    +0.15
    0.5%
    193
    +0.15
    0.5%
    345
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.15
    0.08
    326
    +0.15
    0.12
    621
    +0.15
    0.09
    Negative Logits
    é»Ĵ
    -0.85
    Coun
    -0.83
     Grac
    -0.82
    google
    -0.81
    uncture
    -0.81
    utm
    -0.81
     NEO
    -0.79
    ä¿
    -0.79
    adobe
    -0.79
     USPS
    -0.77
    POSITIVE LOGITS
    DER
    0.84
    gettable
    0.83
    bsite
    0.80
     parity
    0.79
    estine
    0.79
     accompanying
    0.79
     hooked
    0.78
     equivalents
    0.77
    scl
    0.77
    ADRA
    0.77
    Activations Density 2.840%

    No Known Activations