© 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. 2-RES-JB
    11. 9347
    Prev
    Next
    INDEX
    Explanations

    mentions of municipal-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to municipal governance and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -1.11
    vier
    -0.85
    psons
    -0.77
    dates
    -0.77
    zees
    -0.76
    heimer
    -0.75
    reen
    -0.74
    ombs
    -0.74
    lyn
    -0.73
    alia
    -0.73
    POSITIVE LOGITS
     municipal
    1.05
    unicip
    0.99
     councillor
    0.88
     wastewater
    0.87
     sewage
    0.86
     municipality
    0.81
     municipalities
    0.80
     delinqu
    0.79
     Auditor
    0.78
     mayor
    0.78
    Activations Density 0.005%

    No Known Activations