© 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. 40594
    Prev
    Next
    INDEX
    Explanations

    news articles about various individuals, events, and industry developments, with a focus on music, space launches, community initiatives, and legal cases related to human rights

    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
    266
    +0.27
    1.4%
    447
    +0.21
    1.1%
    720
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.27
    0.13
    393
    +0.21
    0.69
    78
    +0.11
    0.08
    Negative Logits
    obos
    -0.73
    uss
    -0.65
     Defin
    -0.61
    OF
    -0.56
    fred
    -0.56
    linux
    -0.53
    Ec
    -0.52
    Fred
    -0.52
    Boost
    -0.51
    Die
    -0.50
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.66
     hijab
    0.64
     Karachi
    0.62
     Ichigo
    0.61
    iferation
    0.57
    ollah
    0.56
    olescent
    0.56
    hran
    0.56
    dayName
    0.55
    AME
    0.54
    Activations Density 85.031%

    No Known Activations