© 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. 1-RES-JB
    11. 3445
    Prev
    Next
    INDEX
    Explanations

    statements or actions that happen immediately after a specific trigger or event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Upon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammad
    -0.72
    ammy
    -0.69
    Rub
    -0.66
    omsday
    -0.66
    acea
    -0.65
     SPL
    -0.65
    ajo
    -0.65
    amen
    -0.64
    PAC
    -0.64
    amd
    -0.63
    POSITIVE LOGITS
    Upon
    1.14
     Upon
    1.06
     arrival
    0.82
     gratification
    0.79
    ĸļ
    0.78
     inspecting
    0.77
     upon
    0.77
    entimes
    0.76
     veter
    0.76
     unden
    0.76
    Activations Density 0.004%

    No Known Activations