© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22329
    Prev
    Next
    INDEX
    Explanations

    words related to official proceedings or documents, specifically related to voting or legislation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific term related to a legislative or formal process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥŁ
    -0.97
    ãĤ»
    -0.91
    ãĥģ
    -0.82
    IOR
    -0.82
    ãĥ¤
    -0.80
    ãĥĨãĤ£
    -0.76
    ilar
    -0.73
    itars
    -0.73
    ãĥIJ
    -0.72
    ãĥĺãĥ©
    -0.71
    POSITIVE LOGITS
    Roll
    1.21
     Roll
    1.17
     Rolls
    0.98
    roll
    0.97
     roll
    0.96
    rolling
    0.88
    sheet
    0.85
     rolls
    0.85
     rolling
    0.85
     rolled
    0.84
    Activations Density 0.007%

    No Known Activations