© 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. 35234
    Prev
    Next
    INDEX
    Explanations

    statements indicating support or lack of support

    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
    288
    +0.10
    0.6%
    496
    +0.10
    0.5%
    61
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.10
    0.17
    618
    +0.10
    0.11
    131
    +0.09
    0.06
    Negative Logits
    naire
    -0.65
    naires
    -0.64
    apeake
    -0.62
    isson
    -0.62
    ogy
    -0.62
    »Ĵ
    -0.61
     Nanto
    -0.58
     Sed
    -0.57
    bats
    -0.56
    APTER
    -0.56
    POSITIVE LOGITS
     unsupported
    0.85
     ï
    0.67
     guiIcon
    0.65
    PLIED
    0.65
     guiActive
    0.64
    iframe
    0.62
     Advertisement
    0.57
    atre
    0.57
    taboola
    0.57
     Loading
    0.57
    Activations Density 8.181%

    No Known Activations