© 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. 0-RES-JB
    11. 16363
    Prev
    Next
    INDEX
    Explanations

    locations related to the state of Pennsylvania

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Pennsylvania

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢ
    -0.75
     arte
    -0.74
     analys
    -0.74
    âĶ
    -0.72
     armour
    -0.71
     util
    -0.70
     apologise
    -0.69
     Deng
    -0.67
    yang
    -0.67
     jungle
    -0.65
    POSITIVE LOGITS
     Pennsylvania
    3.57
    Penn
    2.52
     Delaware
    2.05
    sylvania
    2.01
     Maryland
    1.98
     Penn
    1.98
     Ohio
    1.93
     Philadelphia
    1.91
     Massachusetts
    1.89
     Michigan
    1.88
    Activations Density 0.011%

    No Known Activations