© 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 EvalsExportsinterp-engineNEWAPI 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. 1108
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Discuss" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "discuss" and its variations

    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
    bott
    -0.69
    warm
    -0.67
    onew
    -0.67
    Torrent
    -0.65
    fits
    -0.65
    execute
    -0.64
    guard
    -0.64
    Ms
    -0.63
    uilt
    -0.63
    fighters
    -0.63
    POSITIVE LOGITS
     topics
    1.11
     specifics
    0.86
     how
    0.84
     whether
    0.83
     aspects
    0.81
     matters
    0.77
     possibilities
    0.76
     issues
    0.76
     alternatives
    0.75
     subjects
    0.72
    Activations Density 0.046%

    No Known Activations