© 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. 10-RES-JB
    11. 19014
    Prev
    Next
    INDEX
    Explanations

    the word "happen" or its variations in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "happen" and its variations in various contexts

    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
    utz
    -0.57
    ware
    -0.56
    ocker
    -0.56
     Innov
    -0.51
     Advocate
    -0.51
     viable
    -0.50
     Efficiency
    -0.50
     interpretation
    -0.49
     turf
    -0.49
    ilts
    -0.48
    POSITIVE LOGITS
    llor
    0.76
     upon
    0.74
    ALLY
    0.74
     to
    0.72
    uations
    0.72
    rils
    0.72
    idently
    0.70
    uate
    0.69
    ean
    0.69
    upon
    0.69
    Activations Density 0.032%

    No Known Activations