© 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. 1-RES-JB
    11. 20485
    Prev
    Next
    INDEX
    Explanations

    references or mentions of images or pictures

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic or theme denoted by "TY."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    esville
    -0.72
    quist
    -0.70
    raised
    -0.68
    aunder
    -0.64
     Greenwald
    -0.62
     Manit
    -0.62
    Downloadha
    -0.62
    stellar
    -0.61
    itch
    -0.61
    acea
    -0.61
    POSITIVE LOGITS
    TY
    1.58
     IMAGES
    1.27
    ENCY
    0.85
    URE
    0.84
    IFF
    0.78
    ISM
    0.76
    nergy
    0.76
    APE
    0.74
     sandwiches
    0.73
    tymology
    0.73
    Activations Density 0.002%

    No Known Activations