© 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. 31131
    Prev
    Next
    INDEX
    Explanations

    proper nouns (names of places and people)

    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
    26
    +0.14
    0.7%
    526
    +0.11
    0.6%
    386
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.23
    314
    +0.11
    -0.04
    232
    +0.10
    0.10
    Negative Logits
     Nadu
    -0.79
    aneous
    -0.71
    zanne
    -0.70
    ptin
    -0.69
    ffic
    -0.68
    pper
    -0.68
    lda
    -0.65
    escal
    -0.61
    arma
    -0.61
    ittee
    -0.59
    POSITIVE LOGITS
    acle
    1.08
    acles
    1.07
    aby
    1.04
    yard
    0.94
    abies
    0.91
    owitz
    0.88
    oreal
    0.85
    Barn
    0.81
    ificial
    0.80
    aul
    0.79
    Activations Density 8.539%

    No Known Activations