© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1939
    Prev
    Next
    INDEX
    Explanations

    names of individuals related to Russian politics and history

    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
    699
    +0.16
    0.6%
    339
    +0.13
    0.5%
    563
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.14
    326
    +0.13
    0.16
    288
    +0.11
    0.19
    Negative Logits
    dress
    -0.89
    roads
    -0.82
    runner
    -0.76
    wal
    -0.75
    leaf
    -0.75
    gate
    -0.74
    ModLoader
    -0.74
    makers
    -0.74
    Score
    -0.73
    resp
    -0.73
    POSITIVE LOGITS
    akov
    1.27
    kaya
    1.23
    achev
    1.20
    opol
    1.15
    ovsky
    1.13
    chenko
    1.10
     Mikhail
    1.05
     Dmitry
    1.04
     Dmit
    1.02
     Putin
    1.00
    Activations Density 4.153%

    No Known Activations