© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 6279
    Prev
    Next
    INDEX
    Explanations

    text related to technological tasks and programming

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to tasks, activities, or suggestions for engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    escription
    -0.65
    yss
    -0.60
    ropolitan
    -0.59
    verning
    -0.59
    utsche
    -0.58
    anamo
    -0.57
    xtap
    -0.56
    aples
    -0.56
    recated
    -0.56
    inventoryQuantity
    -0.54
    POSITIVE LOGITS
     someday
    1.09
     ASAP
    1.03
     :)
    0.97
     ;)
    0.97
     :-)
    0.89
     ðŁĻĤ
    0.88
     anytime
    0.88
    !.
    0.87
     instead
    0.86
    *.
    0.85
    Activations Density 1.317%

    No Known Activations