© 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. 2711
    Prev
    Next
    INDEX
    Explanations

    the names of political figures serving as mayors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mayors and their corresponding names

    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
    dates
    -0.79
    arial
    -0.78
    endish
    -0.77
    reen
    -0.73
     instruments
    -0.72
    pmwiki
    -0.71
     notebooks
    -0.71
    FUL
    -0.70
    dragon
    -0.69
    MpServer
    -0.69
    POSITIVE LOGITS
    alty
    1.41
     mayoral
    1.01
     borough
    0.94
     Mayor
    0.92
    alties
    0.90
    Mayor
    0.90
     mayor
    0.86
     oun
    0.85
     councillor
    0.79
     Blasio
    0.75
    Activations Density 0.034%

    No Known Activations