© 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. 9-RES-JB
    11. 15601
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Andre" at varying strengths which may suggest a specific focus or interest on entities related to Andre

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Andre."

    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
    inct
    -0.87
    ulhu
    -0.75
    ead
    -0.70
    ointed
    -0.70
    manship
    -0.69
    stellar
    -0.68
    elled
    -0.66
    eled
    -0.66
    lishing
    -0.65
    dfx
    -0.65
    POSITIVE LOGITS
    tti
    1.21
    essen
    1.05
    byss
    0.83
    cats
    0.80
     3000
    0.73
    ques
    0.71
     Vu
    0.71
     Paste
    0.71
     Damon
    0.69
    gie
    0.67
    Activations Density 0.043%

    No Known Activations