© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 14868
    Prev
    Next
    INDEX
    Explanations

    references to universities, specifically focusing on Purdue University and individuals like Karl Rove associated with it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific universities and political figures, particularly Purdue University and Karl Rove

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

    No Comments

    Negative Logits
    ials
    -0.95
    ially
    -0.89
    ual
    -0.89
    ually
    -0.88
    ividual
    -0.85
    abilia
    -0.83
    ias
    -0.83
    iation
    -0.82
    ariat
    -0.80
    ians
    -0.80
    POSITIVE LOGITS
    tin
    0.90
    irie
    0.86
    din
    0.80
    due
    0.79
     Blooming
    0.78
    tto
    0.75
    doors
    0.74
    tale
    0.74
    ttes
    0.73
    brush
    0.71
    Activations Density 0.028%

    No Known Activations