© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3416
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses starting with the word "which"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with the word "which."

    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
     VIDEOS
    -0.86
     Bed
    -0.75
    politics
    -0.74
     Bedford
    -0.65
     Tanz
    -0.65
    MENTS
    -0.65
    STE
    -0.62
    let
    -0.61
     Baker
    -0.61
     Anything
    -0.60
    POSITIVE LOGITS
    soever
    0.91
     resulted
    0.86
     comprises
    0.85
     enables
    0.79
     brings
    0.78
     incidentally
    0.78
     exposes
    0.78
     contains
    0.77
     includes
    0.77
    iao
    0.76
    Activations Density 0.083%

    No Known Activations