© 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. 19404
    Prev
    Next
    INDEX
    Explanations

    instances of the word "standing on"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "standing on."

    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
    ults
    -0.69
    anan
    -0.66
    inations
    -0.62
    YY
    -0.62
    rament
    -0.61
    ividual
    -0.59
    bats
    -0.59
    lance
    -0.59
    ²¾
    -0.58
    ynt
    -0.57
    POSITIVE LOGITS
     top
    0.97
     rooft
    0.97
    eday
    0.92
     behalf
    0.91
    shore
    0.86
    top
    0.83
     fumes
    0.82
    site
    0.82
     roofs
    0.82
     shore
    0.80
    Activations Density 0.154%

    No Known Activations