© 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. 7774
    Prev
    Next
    INDEX
    Explanations

    Words related to popular culture, specifically music and entertainment industry references, particularly those involving Jay Z

    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
    659
    +0.20
    0.6%
    443
    +0.17
    0.5%
    240
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.06
    443
    +0.17
    0.03
    76
    +0.16
    0.04
    Negative Logits
    htaking
    -1.33
    cffff
    -1.15
    milo
    -1.15
    bably
    -1.14
    atform
    -1.13
    rontal
    -1.12
    ancial
    -1.11
    iture
    -1.09
    ¥ŀ
    -1.06
     foss
    -1.02
    POSITIVE LOGITS
    hawks
    1.71
    hawk
    1.52
    Jay
    1.40
    lon
    1.30
    walking
    1.21
     Jay
    1.20
    mill
    1.17
    mes
    1.15
    jay
    1.15
     Dee
    1.15
    Activations Density 0.754%

    No Known Activations