© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15067
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    place names, specifically cities and towns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The final token of proper nouns of places

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¯
    -0.77
     sacrific
    -0.73
    omal
    -0.72
    rahim
    -0.72
    thood
    -0.71
    ãĥĻ
    -0.70
    ror
    -0.69
    intern
    -0.69
    grave
    -0.68
    onym
    -0.68
    POSITIVE LOGITS
     County
    1.09
     Airport
    1.02
     Township
    1.01
     Heights
    0.96
     City
    0.94
     Springs
    0.93
     Municipal
    0.92
     metro
    0.91
     Harbor
    0.90
     Junction
    0.89
    Activations Density 0.148%

    No Known Activations