© 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. 35754
    Prev
    Next
    INDEX
    Explanations

    proper names, potentially related to news events or cultural references

    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
    +0.18
    0.9%
    659
    +0.11
    0.6%
    496
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    577
    +0.18
    0.12
    338
    +0.11
    0.12
    112
    +0.09
    0.11
    Negative Logits
    unct
    -0.76
    rious
    -0.74
    itious
    -0.72
    itous
    -0.70
    ilib
    -0.69
    rontal
    -0.68
    odic
    -0.67
    rous
    -0.67
    icket
    -0.66
    ocr
    -0.64
    POSITIVE LOGITS
    Anne
    0.79
    wei
    0.74
    lee
    0.68
    anne
    0.68
    lean
    0.67
    baugh
    0.66
    burg
    0.65
    lees
    0.64
    avin
    0.64
    vers
    0.63
    Activations Density 13.176%

    No Known Activations