© 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. 33391
    Prev
    Next
    INDEX
    Explanations

    keywords related to news articles

    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
    640
    +0.18
    0.9%
    373
    +0.11
    0.6%
    236
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.44
    160
    +0.11
    0.26
    373
    +0.10
    -0.17
    Negative Logits
    ueller
    -0.58
     concludes
    -0.57
    ãĤ©
    -0.54
    collect
    -0.53
     gmaxwell
    -0.53
    _.
    -0.52
     someday
    -0.52
     exclaim
    -0.52
     commissions
    -0.52
     deduct
    -0.52
    POSITIVE LOGITS
     Latest
    0.68
    ccording
    0.67
    roversial
    0.62
    Sorry
    0.61
    hello
    0.57
    Gun
    0.56
    everal
    0.56
    PORT
    0.55
    LOS
    0.55
    Property
    0.53
    Activations Density 8.215%

    No Known Activations