© 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 Local
    9. 6-RES_SCL-AJT
    11. 37216
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguments, discussions, and opinions

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.35
    1.6%
    679
    +0.16
    0.7%
    195
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.35
    0.25
    283
    +0.16
    0.02
    33
    +0.13
    0.10
    Negative Logits
    psy
    -0.68
    beam
    -0.67
    mental
    -0.65
     Seym
    -0.62
    obyl
    -0.61
     Radiation
    -0.59
    ecycle
    -0.59
    plant
    -0.59
    7601
    -0.59
    cler
    -0.58
    POSITIVE LOGITS
     vehemently
    0.91
     convinc
    0.89
     forcefully
    0.87
     against
    0.87
     persu
    0.83
     passionately
    0.81
     arguing
    0.81
    inet
    0.80
     argue
    0.80
     arguments
    0.78
    Activations Density 14.595%

    No Known Activations