© 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. 8-RES-JB
    11. 6286
    Prev
    Next
    INDEX
    Explanations

    sentences starting with 'It' followed by a verb or verb phrase

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "It" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */
    -0.75
    ************
    -0.72
    models
    -0.70
    ignty
    -0.69
    hips
    -0.64
     respons
    -0.64
    itatively
    -0.63
    OTHER
    -0.63
    aires
    -0.63
    mission
    -0.62
    POSITIVE LOGITS
    zbollah
    1.01
    onut
    0.76
    chwitz
    0.76
     Begins
    0.74
     dawn
    0.73
     crept
    0.71
     rains
    0.69
    loo
    0.67
     Might
    0.64
    endor
    0.64
    Activations Density 0.125%

    No Known Activations