© 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. 6343
    Prev
    Next
    INDEX
    Explanations

    hints or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    references to hints or indications about the future

    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
    ruciating
    -0.73
    ÄŁ
    -0.70
    vict
    -0.69
     seiz
    -0.66
    exper
    -0.64
    lux
    -0.61
    psc
    -0.61
    rament
    -0.61
     unequ
    -0.60
    scrib
    -0.60
    POSITIVE LOGITS
     hint
    1.43
     hints
    1.32
     clues
    1.07
     hinted
    1.04
     clue
    1.00
     glimps
    0.94
     towards
    0.79
     toward
    0.77
     glimpse
    0.73
    ère
    0.73
    Activations Density 0.117%

    No Known Activations