© 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. 10417
    Prev
    Next
    INDEX
    Explanations

    terms related to research findings or study results

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific findings or results

    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
     chopping
    -0.72
     actionGroup
    -0.66
    skill
    -0.65
    resent
    -0.65
     Bride
    -0.64
    IDES
    -0.63
     Spice
    -0.63
    tz
    -0.62
    bid
    -0.62
     maiden
    -0.62
    POSITIVE LOGITS
     findings
    0.95
    iveness
    0.84
     corrobor
    0.82
     pertaining
    0.81
     regarding
    0.78
     dispro
    0.77
    iments
    0.76
     concerning
    0.76
    itutional
    0.72
    ivism
    0.71
    Activations Density 0.056%

    No Known Activations