© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 12900
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a strong opinion or a firm declaration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express honesty or confront uncomfortable truths

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ourses
    -0.74
    arching
    -0.71
    pread
    -0.70
    emis
    -0.67
    ilater
    -0.67
    zag
    -0.67
    ãĥĻ
    -0.66
    andel
    -0.65
    ailability
    -0.64
    guided
    -0.63
    POSITIVE LOGITS
    ,
    0.96
    ,.
    0.85
    ,...
    0.83
     though
    0.81
    :
    0.79
    :,
    0.76
    ,,
    0.71
    ;
    0.71
     folks
    0.71
     guys
    0.70
    Activations Density 0.168%

    No Known Activations