© 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. 45720
    Prev
    Next
    INDEX
    Explanations

    dates and time-related phrases

    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
    +0.17
    1.2%
    218
    +0.09
    0.6%
    393
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.28
    393
    +0.09
    0.28
    375
    +0.07
    0.05
    Negative Logits
    mil
    -0.45
    .-
    -0.41
    arel
    -0.39
    jp
    -0.39
    Car
    -0.38
     Cosponsors
    -0.38
    .--
    -0.37
    pots
    -0.37
    arious
    -0.36
    gra
    -0.36
    POSITIVE LOGITS
     reckoning
    0.53
    rison
    0.50
     arrival
    0.50
     hostilities
    0.49
    uberty
    0.49
     onset
    0.48
    eme
    0.47
     filming
    0.47
    onement
    0.45
     totality
    0.44
    Activations Density 11.425%

    No Known Activations