© 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. 7-RES-JB
    11. 12549
    Prev
    Next
    INDEX
    Explanations

    questions introduced by the word "Which"

    oai_token-act-pair · gpt-3.5-turbo

    questions or clauses that begin with "Which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pees
    -0.70
    chet
    -0.70
    gy
    -0.70
    borg
    -0.66
    burg
    -0.66
    larg
    -0.64
    bug
    -0.64
    Gy
    -0.63
    usive
    -0.63
    ge
    -0.62
    POSITIVE LOGITS
     brings
    0.96
     begs
    0.88
    soever
    0.78
     incidentally
    0.76
     admittedly
    0.75
     translates
    0.70
    odox
    0.70
     leads
    0.69
     reminds
    0.69
     resulted
    0.68
    Activations Density 0.056%

    No Known Activations