© 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. 2-RES-JB
    11. 17419
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental bodies such as legislatures in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies and their members

    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
    thritis
    -0.90
    eous
    -0.74
    reci
    -0.68
     Squirrel
    -0.68
    licted
    -0.68
    zl
    -0.68
    elli
    -0.67
    stocks
    -0.66
    tle
    -0.66
    iak
    -0.66
    POSITIVE LOGITS
    interstitial
    0.98
    atures
    0.91
     legislature
    0.89
     legislators
    0.84
     legislator
    0.84
     legislatures
    0.82
     senate
    0.77
    otine
    0.76
    itol
    0.75
    ignty
    0.73
    Activations Density 0.017%

    No Known Activations