© 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. 9-RES-JB
    11. 15962
    Prev
    Next
    INDEX
    Explanations

    the name "Stewart" followed by either 'art' or numbered variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Stewart

    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
    cles
    -0.90
    BLE
    -0.88
    ptive
    -0.80
    nesia
    -0.76
    ilar
    -0.74
    ptives
    -0.72
    phant
    -0.71
    ucl
    -0.71
    opathic
    -0.71
    ply
    -0.70
    POSITIVE LOGITS
     Stewart
    0.82
    ards
    0.76
    ie
    0.72
     Downing
    0.72
    fried
    0.72
     Olsen
    0.68
    ieri
    0.68
     Rollins
    0.68
    ry
    0.66
    odd
    0.65
    Activations Density 0.078%

    No Known Activations