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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13054
    Prev
    Next
    INDEX
    Explanations

    data related to economic statistics and government studies

    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
    447
    +0.31
    1.6%
    497
    +0.10
    0.5%
    731
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.31
    0.39
    283
    +0.10
    0.01
    14
    +0.10
    0.06
    Negative Logits
    dit
    -0.67
     completes
    -0.62
     appl
    -0.61
     succeeds
    -0.60
     particulars
    -0.59
     marqu
    -0.59
     wills
    -0.59
     wishes
    -0.57
     obscurity
    -0.57
    aptic
    -0.57
    POSITIVE LOGITS
    Average
    0.83
    Ranked
    0.80
    adjusted
    0.80
     averaging
    0.78
     average
    0.78
     Percentage
    0.77
     unsustainable
    0.74
     (%
    0.73
     estimated
    0.71
     projected
    0.71
    Activations Density 23.733%

    No Known Activations