© 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. 10-RES-JB
    11. 5838
    Prev
    Next
    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    significant events or milestones

    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
     Sometimes
    -0.67
    mons
    -0.66
    hide
    -0.65
    angler
    -0.64
    ___
    -0.60
    onite
    -0.60
     advises
    -0.59
    ourke
    -0.59
     Amen
    -0.58
     Occasionally
    -0.58
    POSITIVE LOGITS
     anticipation
    1.17
     congratulations
    1.17
     awaited
    1.01
    Congratulations
    0.99
     hailed
    0.97
     pundits
    0.95
    anticipated
    0.95
     understandably
    0.92
     Congratulations
    0.92
     excitement
    0.90
    Activations Density 0.856%

    No Known Activations