© 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. 2277
    Prev
    Next
    INDEX
    Explanations

    proper names or titles, specifically finding occurrences of the name "Victor" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Victor" and its variations

    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
    shed
    -0.81
    nesses
    -0.77
    STER
    -0.77
    quarters
    -0.76
    BOOK
    -0.73
    ness
    -0.73
    Ħ¢
    -0.69
    CAST
    -0.68
    scl
    -0.68
    shaw
    -0.67
    POSITIVE LOGITS
     Hugo
    1.15
    inus
    0.98
    iana
    0.94
    ians
    0.90
    itate
    0.88
    inia
    0.86
    iculture
    0.85
     Ortiz
    0.84
    ines
    0.84
    ine
    0.81
    Activations Density 0.044%

    No Known Activations