© 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. 36921
    Prev
    Next
    INDEX
    Explanations

    words and phrases in a foreign language

    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
    48
    +0.11
    0.5%
    107
    +0.11
    0.5%
    23
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.04
    742
    +0.11
    0.04
    103
    +0.11
    0.05
    Negative Logits
    enegger
    -0.89
    anwhile
    -0.86
    cliffe
    -0.84
    nels
    -0.79
    butt
    -0.74
    kefeller
    -0.74
     WARN
    -0.74
    Interstitial
    -0.74
     bearer
    -0.70
    swick
    -0.69
    POSITIVE LOGITS
    ħ
    1.94
    ĩ
    1.78
    Ĩ
    1.74
    İ
    1.69
    Ī
    1.64
    Ķ
    1.64
    Ħ
    1.60
    ī
    1.57
    ķ
    1.56
    ĸ
    1.50
    Activations Density 3.677%

    No Known Activations