© 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. 7869
    Prev
    Next
    INDEX
    Explanations

    famous individuals named Sarah, particularly Sarah Palin, and mentions of key information or controversies related to her

    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
    201
    +0.17
    0.6%
    346
    +0.17
    0.6%
    274
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.08
    346
    +0.17
    0.07
    201
    +0.14
    0.06
    Negative Logits
    awaru
    -1.23
     nomine
    -1.19
    ographed
    -1.12
    ebin
    -1.10
    essee
    -1.04
    OWER
    -0.97
    eering
    -0.97
    omething
    -0.96
    rosse
    -0.94
     administr
    -0.94
    POSITIVE LOGITS
     Palin
    1.55
     Jane
    1.24
     Connor
    1.20
     Koen
    1.18
     McL
    1.12
    mers
    1.08
     Palmer
    1.06
    ding
    1.06
    GE
    1.06
    GES
    1.05
    Activations Density 1.298%

    No Known Activations