© 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. 12-RES-JB
    11. 2278
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and titles of books and news outlets

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to authors and their works

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     conduc
    -0.73
     misunder
    -0.67
     incent
    -0.66
    ngth
    -0.64
     shenan
    -0.63
    neau
    -0.63
    soDeliveryDate
    -0.62
    credit
    -0.62
     Franç
    -0.61
     horizont
    -0.61
    POSITIVE LOGITS
    oby
    0.55
    ream
    0.53
     lob
    0.52
     indoctr
    0.52
     tens
    0.51
     ante
    0.51
    raised
    0.49
    owitz
    0.49
    Ĥİ
    0.49
     seizures
    0.49
    Activations Density 0.062%

    No Known Activations