© 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. 4871
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and technical details from books and projects

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

    references to publications, including details such as ISBN numbers and publication dates

    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
    CP
    -1.01
    PC
    -0.90
     Cambodia
    -0.88
     Cambod
    -0.86
    cb
    -0.85
     Caps
    -0.85
    PAC
    -0.81
    CB
    -0.81
    caps
    -0.81
    bp
    -0.81
    POSITIVE LOGITS
     Eliot
    0.80
    ieu
    0.78
    ilda
    0.78
    INE
    0.76
     Elliot
    0.73
     332
    0.73
     338
    0.72
    ini
    0.71
    331
    0.71
    337
    0.71
    Activations Density 1.007%

    No Known Activations