© 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 EvalsExportsAPI 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. 391
    Prev
    Next
    INDEX
    Explanations

    mentions of the Auburn University football team

    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
    340
    +0.17
    0.5%
    660
    +0.16
    0.5%
    562
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.17
    0.04
    660
    +0.16
    0.04
    581
    +0.14
    0.04
    Negative Logits
    estyles
    -1.18
    utenberg
    -1.07
    abwe
    -1.06
     precincts
    -1.02
     Mechdragon
    -1.01
     sidx
    -1.00
    00007
    -1.00
     DPRK
    -0.95
    uania
    -0.94
     Earthqu
    -0.94
    POSITIVE LOGITS
    pillar
    1.37
    alon
    1.23
    otropic
    1.14
    heim
    1.13
    ertain
    1.10
    asia
    1.09
    mentioned
    1.07
    ritz
    1.06
    iliary
    1.03
    reau
    1.02
    Activations Density 0.676%

    No Known Activations