© 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. 10-RES-JB
    11. 14111
    Prev
    Next
    INDEX
    Explanations

    mentions of specific villages

    oai_token-act-pair · gpt-3.5-turbo

    references to villages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸
    -0.82
    pter
    -0.81
    sis
    -0.75
    rencies
    -0.75
    xon
    -0.75
    inventoryQuantity
    -0.75
    henko
    -0.74
    ueller
    -0.74
    furt
    -0.73
    vable
    -0.73
    POSITIVE LOGITS
    folk
    0.96
     elders
    0.96
     village
    0.94
     villages
    0.92
     councils
    0.87
     elder
    0.86
     Shal
    0.84
     outpost
    0.82
     halls
    0.81
     cemetery
    0.78
    Activations Density 0.035%

    No Known Activations