© 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. 8684
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or events in New York

    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
    606
    +0.10
    0.4%
    60
    +0.09
    0.4%
    608
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.04
    57
    +0.09
    0.03
    296
    +0.09
    0.04
    Negative Logits
     Tata
    -0.73
    izen
    -0.72
    antha
    -0.71
     Tayyip
    -0.71
    hran
    -0.70
    Maker
    -0.70
    months
    -0.69
     Aadhaar
    -0.67
    fen
    -0.67
     Narendra
    -0.66
    POSITIVE LOGITS
    CLASSIFIED
    0.84
    UL
    0.78
    LV
    0.76
    sylv
    0.75
    UGE
    0.75
    ILLE
    0.74
     ILCS
    0.72
    urses
    0.72
    MG
    0.71
    FORMATION
    0.71
    Activations Density 0.441%

    No Known Activations