© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35681
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions and corporate history

    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
    762
    +0.12
    0.6%
    268
    +0.09
    0.4%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.12
    0.43
    138
    +0.09
    0.40
    64
    +0.09
    -0.26
    Negative Logits
     Coy
    -0.66
     Adin
    -0.59
     Pear
    -0.59
     lawy
    -0.59
    uador
    -0.57
     Hyde
    -0.55
     Kazakh
    -0.55
     Quan
    -0.54
     Scalia
    -0.54
    bern
    -0.53
    POSITIVE LOGITS
    assetsadobe
    0.73
    PLIED
    0.69
    opus
    0.69
    ;;;;;;;;;;;;
    0.67
    urations
    0.64
     Manufacturer
    0.62
    amide
    0.59
    ushima
    0.58
     inhibitor
    0.58
    terior
    0.58
    Activations Density 17.328%

    No Known Activations