© 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. 2030
    Prev
    Next
    INDEX
    Explanations

    mentions of political entities, specifically those related to the Democratic Republic

    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
    288
    +0.21
    0.8%
    167
    +0.21
    0.8%
    339
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.21
    0.07
    288
    +0.21
    0.06
    339
    +0.15
    0.05
    Negative Logits
    paio
    -1.11
    anamo
    -1.04
    trak
    -0.99
    olkien
    -0.95
    uses
    -0.90
     Clever
    -0.90
    uated
    -0.89
    asus
    -0.88
    laus
    -0.88
    krit
    -0.86
    POSITIVE LOGITS
     Republic
    1.08
     Party
    1.00
     frontrunner
    0.98
     stronghold
    0.98
    ity
    0.96
     strongh
    0.95
     Instit
    0.92
     conventions
    0.91
     rites
    0.90
     correctness
    0.90
    Activations Density 0.470%

    No Known Activations