© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 20833
    Prev
    Next
    INDEX
    Explanations

    images with captions

    oai_token-act-pair · gpt-3.5-turbo

    images and their associated captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dies
    -0.86
    halla
    -0.79
    merce
    -0.72
    laws
    -0.72
    tons
    -0.72
    »Ĵ
    -0.71
    die
    -0.69
    anders
    -0.69
    ueless
    -0.69
    achus
    -0.68
    POSITIVE LOGITS
     caption
    1.38
     copyright
    1.21
     Gallery
    0.95
     gallery
    0.94
     Courtesy
    0.93
    Image
    0.93
     Image
    0.89
     Images
    0.87
     Source
    0.86
     Comics
    0.85
    Activations Density 0.016%

    No Known Activations