© 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. 10159
    Prev
    Next
    INDEX
    Explanations

    technical terms and information related to programming languages and technology

    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
    498
    +0.16
    0.6%
    651
    +0.13
    0.5%
    313
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.16
    0.11
    739
    +0.13
    0.06
    679
    +0.12
    0.15
    Negative Logits
     Allies
    -0.85
     Mechdragon
    -0.85
     clout
    -0.84
    Label
    -0.82
    ['
    -0.81
     Loch
    -0.79
    Ironically
    -0.78
     charms
    -0.78
     Canaveral
    -0.76
     counterfe
    -0.75
    POSITIVE LOGITS
    posium
    1.10
    endix
    1.07
     discuss
    1.07
    fter
    1.07
     analyse
    1.06
     blog
    1.04
    isode
    1.03
    nesday
    1.01
     tutorial
    1.01
     delve
    1.00
    Activations Density 5.245%

    No Known Activations