© 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 Local
    9. 6-RES_SCL-AJT
    11. 31775
    Prev
    Next
    INDEX
    Explanations

    references to individuals and historical events in texts with religious or political contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    235
    +0.13
    0.6%
    336
    +0.11
    0.5%
    757
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.23
    235
    +0.11
    0.11
    99
    +0.09
    0.10
    Negative Logits
    prise
    -0.63
     canine
    -0.63
    intendent
    -0.62
     Devils
    -0.62
    itors
    -0.62
    phrine
    -0.61
     Rookie
    -0.61
    ior
    -0.60
     DMV
    -0.60
    itor
    -0.58
    POSITIVE LOGITS
    hammad
    0.86
    aji
    0.83
    ishi
    0.82
     Sina
    0.80
     Tay
    0.73
     Saud
    0.72
    aleb
    0.72
    aith
    0.71
    Focus
    0.71
     Imam
    0.70
    Activations Density 9.141%

    No Known Activations