© 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. 7-RES-JB
    11. 1706
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    references to events and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rompt
    -0.80
    itely
    -0.75
    emark
    -0.71
    sect
    -0.70
    Ó
    -0.70
    ubi
    -0.69
    zens
    -0.68
    iffs
    -0.68
    iqu
    -0.68
    icking
    -0.68
    POSITIVE LOGITS
     Includes
    0.96
     Appears
    0.93
    Requires
    0.90
    Includes
    0.89
     Requires
    0.87
     Sold
    0.85
     Uses
    0.82
     Cannot
    0.80
     Contains
    0.80
     Played
    0.79
    Activations Density 0.617%

    No Known Activations