© 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 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. 33314
    Prev
    Next
    INDEX
    Explanations

    years or date ranges

    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
    +0.14
    0.7%
    84
    +0.10
    0.5%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.21
    547
    +0.10
    0.06
    76
    +0.10
    0.11
    Negative Logits
    shaw
    -0.80
    ez
    -0.76
    sheet
    -0.74
    ymes
    -0.68
    icator
    -0.68
    este
    -0.67
    ding
    -0.65
    icated
    -0.64
    amins
    -0.63
    warts
    -0.63
    POSITIVE LOGITS
    å¹
    0.80
    velength
    0.66
     Fuk
    0.65
     vintage
    0.63
    iatric
    0.61
    teenth
    0.60
     Speedway
    0.59
    ocalyptic
    0.59
    isode
    0.58
    ĸļ
    0.58
    Activations Density 7.779%

    No Known Activations