© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 4806
    Prev
    Next
    INDEX
    Explanations

    mentions of specific administrative regions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to local government and administrative entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.85
    Chuck
    -0.82
     Vegas
    -0.81
    renheit
    -0.77
    riel
    -0.74
    kies
    -0.73
    flex
    -0.73
    Join
    -0.72
    Ô
    -0.72
    Americans
    -0.71
    POSITIVE LOGITS
     prosecutor
    1.35
     magistrate
    1.35
     council
    1.33
     councillor
    1.32
     governor
    1.25
     mayor
    1.23
     councils
    1.16
     municipality
    1.15
     parliament
    1.15
     administration
    1.12
    Activations Density 0.196%

    No Known Activations