© 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. 9804
    Prev
    Next
    INDEX
    Explanations

    keywords related to governmental actions in a specific region

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific geographic area, denoted as "province."

    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
    tle
    -0.93
    paces
    -0.90
    artz
    -0.80
    chel
    -0.79
    gers
    -0.78
    ãĥīãĥ©
    -0.78
    gew
    -0.77
    pace
    -0.75
    eor
    -0.75
    berger
    -0.73
    POSITIVE LOGITS
     province
    0.89
    wide
    0.84
     legislatures
    0.83
     provinces
    0.82
     sovere
    0.81
     annexed
    0.77
     legalized
    0.76
     constitu
    0.75
    rendered
    0.72
     unemploy
    0.71
    Activations Density 0.013%

    No Known Activations