© 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 EvalsExportsinterp-engineNEWAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8201
    Prev
    Next
    INDEX
    Explanations

    news articles and information related to current events and media coverage

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.18
    0.8%
    679
    +0.13
    0.6%
    267
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.18
    0.02
    220
    +0.13
    0.02
    586
    +0.12
    0.02
    Negative Logits
    gone
    -0.88
    ffer
    -0.82
    stood
    -0.76
    ilk
    -0.76
    gran
    -0.75
    yip
    -0.75
    gas
    -0.74
    bler
    -0.73
    chest
    -0.73
    wagen
    -0.73
    POSITIVE LOGITS
     Newsp
    0.86
     Press
    0.82
     Images
    0.75
     Leaders
    0.75
     Entertainment
    0.75
    ertain
    0.74
     Organization
    0.74
    Media
    0.74
    Laughs
    0.73
     States
    0.71
    Activations Density 0.099%

    No Known Activations