© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    scientific research institutions and projects

    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
    99
    +0.18
    0.8%
    746
    +0.14
    0.6%
    302
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.18
    0.05
    99
    +0.14
    0.05
    302
    +0.14
    0.05
    Negative Logits
    chest
    -0.85
    thing
    -0.84
    Else
    -0.82
    loo
    -0.81
    butt
    -0.81
    holding
    -0.79
    mania
    -0.74
    åĤ
    -0.74
    many
    -0.71
    amaz
    -0.71
    POSITIVE LOGITS
    urses
    1.09
    ouri
    0.99
    insula
    0.93
    STAR
    0.92
    erd
    0.88
    osuke
    0.87
    umeric
    0.86
    essee
    0.86
    usra
    0.85
    emonic
    0.85
    Activations Density 0.506%

    No Known Activations