© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24210
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically focusing on names like "Oliver."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Oliver."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.87
    essor
    -0.78
    eanor
    -0.75
    Downloadha
    -0.72
    llor
    -0.70
    evil
    -0.68
    hz
    -0.68
    arching
    -0.67
    Ħ¢
    -0.67
    yg
    -0.66
    POSITIVE LOGITS
     Twist
    0.96
     Crom
    0.90
     Wend
    0.83
    sson
    0.83
     Oliver
    0.80
     Kahn
    0.73
     Klein
    0.72
    pedia
    0.72
    sen
    0.72
     Wilde
    0.71
    Activations Density 0.030%

    No Known Activations