© 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. 2-RES-JB
    11. 24223
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to the state of Pennsylvania

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Pennsylvania

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gers
    -0.85
    lasses
    -0.83
    ged
    -0.82
    ging
    -0.78
    uers
    -0.78
    eer
    -0.77
    lass
    -0.76
    selage
    -0.75
    ynt
    -0.72
    ever
    -0.71
    POSITIVE LOGITS
    sylvania
    1.39
     Pennsylvania
    1.02
     Railroad
    0.99
    sburgh
    0.97
     Berks
    0.94
     Avenue
    0.94
     Township
    0.93
    Penn
    0.92
     Borough
    0.92
     Penn
    0.90
    Activations Density 0.007%

    No Known Activations