© 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. 33473
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Hard" at relatively high activation levels

    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
    +0.11
    0.8%
    496
    +0.09
    0.6%
    247
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.38
    6
    +0.09
    0.19
    442
    +0.07
    0.11
    Negative Logits
    uality
    -0.56
    allery
    -0.47
    umbn
    -0.46
    ĸļ
    -0.45
    uations
    -0.44
     Emir
    -0.43
    oration
    -0.41
     Shutterstock
    -0.40
     Mens
    -0.40
    orative
    -0.39
    POSITIVE LOGITS
    ened
    0.64
    ness
    0.56
    ball
    0.53
    core
    0.52
    iness
    0.52
    iest
    0.51
    ening
    0.51
    Reply
    0.50
    ware
    0.49
    castle
    0.48
    Activations Density 16.836%

    No Known Activations