© 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. 31155
    Prev
    Next
    INDEX
    Explanations

    specific locations mentioned in text related to historic events or personal narratives

    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
    627
    +0.10
    0.5%
    570
    +0.09
    0.5%
    1
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.27
    362
    +0.09
    0.12
    385
    +0.09
    0.14
    Negative Logits
    onna
    -0.66
     tune
    -0.65
    accompan
    -0.64
    ufact
    -0.64
     recomm
    -0.62
     onboard
    -0.61
     relate
    -0.60
     endors
    -0.59
    uctor
    -0.58
     accompanying
    -0.58
    POSITIVE LOGITS
    stad
    0.74
     Territories
    0.72
     Hyde
    0.64
    adelphia
    0.62
    Rect
    0.61
    ategories
    0.61
    abouts
    0.61
    azed
    0.60
    tnc
    0.59
    Mine
    0.59
    Activations Density 10.079%

    No Known Activations