© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8900
    Prev
    Next
    INDEX
    Explanations

    mentions of psychological terms and emotional states, with a focus on potentially negative or intense experiences

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    285
    +0.12
    0.5%
    390
    +0.12
    0.4%
    326
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.14
    48
    +0.12
    0.09
    285
    +0.12
    0.06
    Negative Logits
    andise
    -1.14
    hedral
    -0.93
    aepernick
    -0.85
     Occupations
    -0.83
    ctica
    -0.82
    alyst
    -0.78
    tical
    -0.78
    apor
    -0.77
    ourced
    -0.76
    meal
    -0.76
    POSITIVE LOGITS
    er
    1.43
    erers
    1.27
    ers
    1.22
    ered
    1.21
    enstein
    1.17
    ering
    1.16
    est
    1.16
    ership
    1.07
    ew
    1.04
    erer
    1.00
    Activations Density 2.893%

    No Known Activations