© 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. 16041
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals as founders or co-founders of organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who hold or have held founding positions in organizations or companies

    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
    ureau
    -0.71
    eneg
    -0.70
     Ukrain
    -0.70
    othy
    -0.65
    Deb
    -0.64
    assault
    -0.59
    ascus
    -0.58
     calming
    -0.57
    uchin
    -0.57
     degrading
    -0.57
    POSITIVE LOGITS
    founder
    0.85
     Markus
    0.80
    hips
    0.77
     pains
    0.76
    hip
    0.76
     Alexis
    0.75
    reprene
    0.75
     Founder
    0.74
     Founders
    0.73
     Ezra
    0.73
    Activations Density 0.061%

    No Known Activations