© 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. 40586
    Prev
    Next
    INDEX
    Explanations

    numeric values and locations, potentially related to financial data and population statistics

    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
    644
    +0.15
    0.8%
    114
    +0.11
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.30
    326
    +0.11
    0.24
    151
    +0.10
    0.17
    Negative Logits
    iard
    -0.86
    ening
    -0.85
    bley
    -0.83
    ness
    -0.74
    atri
    -0.74
    usalem
    -0.73
    ened
    -0.72
    hovah
    -0.71
    vern
    -0.71
    lez
    -0.70
    POSITIVE LOGITS
    vier
    0.75
    ulations
    0.67
    Deal
    0.66
    OWS
    0.63
    ulative
    0.62
    Bloom
    0.62
    ulated
    0.61
    amate
    0.61
    Fla
    0.61
    ulators
    0.61
    Activations Density 10.276%

    No Known Activations