© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    specific historical events or people, especially related to geopolitical interactions, influencing the course of 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
    +0.21
    0.8%
    326
    +0.17
    0.7%
    240
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.05
    699
    +0.17
    0.04
    232
    +0.14
    0.05
    Negative Logits
    INC
    -0.90
    HER
    -0.88
     BDS
    -0.85
    uated
    -0.83
    âĸĪâĸĪ
    -0.81
    OHN
    -0.80
     Simulator
    -0.80
     Tuls
    -0.79
     passionate
    -0.79
     Communities
    -0.78
    POSITIVE LOGITS
    wich
    1.34
    querque
    1.18
    lette
    1.13
    wind
    1.11
    lap
    1.11
    ogh
    1.10
    edin
    1.08
    omial
    1.06
    agons
    1.04
    gey
    1.03
    Activations Density 0.611%

    No Known Activations