© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    phrases related to political activities and preparations

    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
    337
    +0.17
    0.6%
    580
    +0.16
    0.6%
    740
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.17
    0.07
    566
    +0.16
    0.06
    337
    +0.13
    0.05
    Negative Logits
     exception
    -0.92
     secondly
    -0.83
    amon
    -0.83
    foundland
    -0.81
     Contributions
    -0.81
     paran
    -0.80
    INC
    -0.79
     assumption
    -0.78
     correlation
    -0.78
     understatement
    -0.78
    POSITIVE LOGITS
    rily
    1.01
    Pie
    0.99
     unfolds
    0.97
     prepares
    0.96
     desperately
    0.91
     progresses
    0.90
     transitioned
    0.89
     thro
    0.88
    ritis
    0.87
     silently
    0.87
    Activations Density 1.191%

    No Known Activations