© 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. 8700
    Prev
    Next
    INDEX
    Explanations

    political and international conflict-related terms

    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
    53
    +0.14
    0.5%
    402
    +0.13
    0.5%
    326
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.14
    0.17
    650
    +0.13
    0.17
    53
    +0.13
    0.16
    Negative Logits
     condem
    -1.17
     clitor
    -1.10
    raints
    -0.99
     clones
    -0.98
     welf
    -0.94
     disadvant
    -0.91
     apes
    -0.91
     womb
    -0.90
     Jinn
    -0.88
    enegger
    -0.88
    POSITIVE LOGITS
    ï¸ı
    1.48
    âĶĢâĶĢ
    1.32
    uthor
    1.15
    vernment
    1.14
    ł
    1.11
    \-
    1.09
    cffffcc
    1.08
    âĸł
    1.08
    oil
    1.08
    1.07
    Activations Density 1.137%

    No Known Activations