© 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. 1236
    Prev
    Next
    INDEX
    Explanations

    examples of situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "For example" or variations of it

    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
    iewicz
    -0.75
    alan
    -0.68
    izzle
    -0.65
    rious
    -0.65
    eat
    -0.64
    ownt
    -0.63
    Moh
    -0.63
    hya
    -0.63
    beat
    -0.61
    itably
    -0.60
    POSITIVE LOGITS
     example
    1.47
     instance
    1.31
     comparison
    1.12
     simplicity
    1.12
     purposes
    1.11
    cing
    1.09
     sake
    1.03
     Example
    1.03
    bidden
    1.01
    got
    0.99
    Activations Density 0.176%

    No Known Activations