© 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. 1-RES-JB
    11. 20004
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific geographical location (Kansas City)

    oai_token-act-pair · gpt-3.5-turbo

    references to Kansas City

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.88
    ãĥĢ
    -0.83
     guiActiveUn
    -0.80
    ãĤ¯
    -0.80
    itably
    -0.79
    ãĥij
    -0.77
    ommel
    -0.77
    ãĥ¼ãĤ¯
    -0.77
    ãĥ¬
    -0.76
    wcsstore
    -0.75
    POSITIVE LOGITS
     City
    1.10
    scape
    1.00
     Chiefs
    0.93
     Mayor
    0.91
    wide
    0.88
     Council
    0.86
     Police
    0.85
     CITY
    0.84
     Municipal
    0.83
     Protocol
    0.82
    Activations Density 0.014%

    No Known Activations