© 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. 7-RES-JB
    11. 3185
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Deb"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Deb" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meal
    -0.84
    faces
    -0.68
    Magikarp
    -0.66
     Inquisitor
    -0.66
    ISTER
    -0.65
    face
    -0.65
    velt
    -0.64
    hetical
    -0.64
     Cth
    -0.63
    */(
    -0.62
    POSITIVE LOGITS
    ilitation
    1.05
    orah
    1.03
    rief
    1.02
    utable
    1.01
    ilit
    0.98
    ilitating
    0.95
    unker
    0.95
    acle
    0.95
    ounced
    0.95
    oard
    0.94
    Activations Density 0.022%

    No Known Activations