© 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. 0-RES-JB
    11. 13378
    Prev
    Next
    INDEX
    Explanations

    verbs related to forcefully throwing or launching something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thrown" 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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĻ¥
    -0.64
    ir
    -0.63
     Trend
    -0.62
     PBS
    -0.61
    eric
    -0.61
    author
    -0.61
    avid
    -0.60
     Tribune
    -0.60
     âĸº
    -0.60
     census
    -0.60
    POSITIVE LOGITS
     thrown
    3.60
     tossed
    2.24
     hurled
    2.19
     flung
    2.00
     throw
    1.64
     threw
    1.59
     throwing
    1.50
     throws
    1.47
    throw
    1.43
    Throw
    1.40
    Activations Density 0.011%

    No Known Activations