© 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. 9-RES-JB
    11. 11272
    Prev
    Next
    INDEX
    Explanations

    hints or indications

    oai_token-act-pair · gpt-3.5-turbo

    expressions that imply suggestions or foreshadowing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lux
    -0.71
    CENT
    -0.71
    rament
    -0.66
    vict
    -0.65
    rior
    -0.64
    ÄŁ
    -0.63
    nea
    -0.63
    ille
    -0.62
    cens
    -0.61
    fare
    -0.61
    POSITIVE LOGITS
     hint
    1.33
     hints
    1.26
     clue
    0.94
     clues
    0.89
     hinted
    0.87
     glimps
    0.78
    ibly
    0.76
     wink
    0.75
     warning
    0.74
    vous
    0.72
    Activations Density 0.074%

    No Known Activations