© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    mentions of city councilors and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of city councilors and related governance terms

    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
     McGee
    -0.73
    hered
    -0.70
     Patient
    -0.68
    Ô
    -0.66
    condition
    -0.65
     Quran
    -0.63
     Virgin
    -0.62
    KA
    -0.62
     Mutual
    -0.62
     PAT
    -0.61
    POSITIVE LOGITS
    cill
    1.38
     councillors
    1.08
    ors
    0.93
    members
    0.93
    aries
    0.92
    Council
    0.89
     Coun
    0.88
     councillor
    0.86
    arin
    0.86
    ruction
    0.85
    Activations Density 0.011%

    No Known Activations