© 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. 10-RES-JB
    11. 772
    Prev
    Next
    INDEX
    Explanations

    instances where something has just happened

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "just"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spread
    -0.66
    risk
    -0.65
    amen
    -0.64
    ENCY
    -0.60
    externalActionCode
    -0.60
    Ultra
    -0.58
     conserve
    -0.58
     disproportionately
    -0.58
    elist
    -0.58
    antage
    -0.58
    POSITIVE LOGITS
    ifiable
    0.99
     finished
    0.98
    ifications
    0.97
     completed
    0.93
     graduated
    0.86
    released
    0.85
    itia
    0.85
    if
    0.85
     launched
    0.82
    ifi
    0.82
    Activations Density 0.044%

    No Known Activations