© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18970
    Prev
    Next
    INDEX
    Explanations

    statements of explanation or justification

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific verb forms that indicate ongoing or significant actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Highlights
    -0.76
    icter
    -0.76
     Cosponsors
    -0.74
     regrets
    -0.72
    vantage
    -0.70
    racuse
    -0.69
    osion
    -0.68
    til
    -0.68
    Cause
    -0.68
    cause
    -0.66
    POSITIVE LOGITS
     technically
    1.06
     ostensibly
    1.01
     purely
    0.93
     essentially
    0.92
     supposed
    0.91
     already
    0.89
     inherently
    0.88
     geographically
    0.88
     predominantly
    0.87
     strictly
    0.87
    Activations Density 0.298%

    No Known Activations