© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13093
    Prev
    Next
    INDEX
    Explanations

    criticisms or negative information related to political figures, particularly involving scandals or accusations

    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
    496
    +0.13
    0.5%
    488
    +0.13
    0.5%
    509
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.02
    326
    +0.13
    0.21
    107
    +0.11
    0.07
    Negative Logits
    Ĥİ
    -0.80
    itialized
    -0.79
     Moonlight
    -0.78
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.75
    ukong
    -0.73
     Immunity
    -0.72
    terness
    -0.71
     degener
    -0.68
     Warp
    -0.66
     turnovers
    -0.66
    POSITIVE LOGITS
    &
    1.16
    daq
    1.11
    ][/
    1.02
    __
    0.94
    fb
    0.93
    %
    0.93
    201
    0.93
    =
    0.91
    003
    0.91
    978
    0.89
    Activations Density 7.749%

    No Known Activations