© 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. 33890
    Prev
    Next
    INDEX
    Explanations

    political and social content such as information about a particular historical event or political movement, critiques of media coverage, and discussions on social issues

    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
    +0.28
    1.5%
    732
    +0.10
    0.5%
    645
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.28
    0.20
    195
    +0.10
    -0.01
    566
    +0.08
    0.14
    Negative Logits
    Reloaded
    -0.57
     Royale
    -0.56
    Interstitial
    -0.56
     Detail
    -0.54
    PF
    -0.54
    %);
    -0.52
    Vert
    -0.52
    milo
    -0.51
     Lima
    -0.50
    ãĥĨ
    -0.50
    POSITIVE LOGITS
    oiler
    0.56
    aucus
    0.55
    endor
    0.55
    hew
    0.55
    emis
    0.54
     caution
    0.53
    went
    0.52
     conclude
    0.52
     parting
    0.52
     sacrific
    0.52
    Activations Density 20.496%

    No Known Activations