© 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. 3-RES-JB
    11. 3617
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the country Syria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PHOTOS
    -0.85
    RAFT
    -0.78
    tumblr
    -0.77
    tub
    -0.73
    enegger
    -0.72
    frame
    -0.72
    VERTIS
    -0.71
    addock
    -0.70
    hered
    -0.69
    hibited
    -0.69
    POSITIVE LOGITS
     Syri
    1.23
    yss
    0.83
     citiz
    0.82
     mosqu
    0.82
    akis
    0.82
     agre
    0.79
     Apost
    0.78
    ignt
    0.75
    igon
    0.74
    iets
    0.72
    Activations Density 0.008%

    No Known Activations