© 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 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. 6-RES-JB
    11. 17807
    Prev
    Next
    INDEX
    Explanations

    phrases indicating upcoming elaboration or emphasis in speech

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or ambivalence about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.76
    cific
    -0.76
    ithing
    -0.73
    igent
    -0.71
    stone
    -0.71
    aintain
    -0.69
    imeter
    -0.65
    hower
    -0.64
    ourses
    -0.64
    atana
    -0.63
    POSITIVE LOGITS
     kidding
    0.90
     damned
    0.76
    oops
    0.73
     hilar
    0.73
     Surprise
    0.73
     Creep
    0.71
     downright
    0.71
     damn
    0.70
     Bucs
    0.70
     darn
    0.69
    Activations Density 1.200%

    No Known Activations