© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8042
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

    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
    393
    +0.17
    0.6%
    608
    +0.14
    0.5%
    286
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.17
    0.13
    393
    +0.14
    0.14
    692
    +0.12
    0.06
    Negative Logits
    comings
    -1.08
    bowl
    -1.05
    facing
    -1.01
    washer
    -0.97
    blems
    -0.97
    incarn
    -0.95
    problem
    -0.93
    initions
    -0.92
    orie
    -0.90
    stakes
    -0.90
    POSITIVE LOGITS
     colleagues
    1.12
     volunteers
    1.11
     assembled
    1.08
     disparate
    1.08
     stakeholders
    1.06
     academics
    1.05
     elders
    1.03
     representatives
    1.02
     allies
    1.02
     dozens
    1.01
    Activations Density 2.939%

    No Known Activations