© 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. 11-RES-JB
    11. 20734
    Prev
    Next
    INDEX
    Explanations

    statistics and projections

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate growth or ongoing conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chero
    -0.64
    letes
    -0.64
    =-=-=-=-
    -0.62
    matical
    -0.62
    ppings
    -0.61
    practice
    -0.61
    fax
    -0.61
    schild
    -0.60
     Awakens
    -0.60
     Supports
    -0.59
    POSITIVE LOGITS
     declining
    1.27
     plummet
    1.25
     decreasing
    1.23
     soaring
    1.20
     rising
    1.18
     shrinking
    1.18
     dwindling
    1.17
     surging
    1.13
     increasing
    1.11
     dropping
    1.10
    Activations Density 0.145%

    No Known Activations