© 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. 1-RES-JB
    11. 16375
    Prev
    Next
    INDEX
    Explanations

    mentions of specific universities and cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of universities and locations, particularly Syracuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teen
    -0.96
    growth
    -0.84
    quer
    -0.82
    ebin
    -0.76
    acting
    -0.75
    jamin
    -0.74
    heid
    -0.73
    ãĥĩãĤ£
    -0.71
    wagen
    -0.69
    eering
    -0.69
    POSITIVE LOGITS
     Syracuse
    0.94
     mosqu
    0.85
     Crunch
    0.84
    kefeller
    0.78
    urses
    0.78
     enthusi
    0.77
     Mysteries
    0.75
     Albany
    0.74
     Rochester
    0.73
     Sapp
    0.72
    Activations Density 0.015%

    No Known Activations