Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3992
    Prev
    Next
    INDEX
    Explanations

    the word "threw" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the verb "threw" and its variations

    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
     Millennium
    -0.62
     ACS
    -0.62
     pastoral
    -0.62
     reciprocal
    -0.61
     Bio
    -0.60
     bio
    -0.59
     Meridian
    -0.58
     capacity
    -0.58
     behalf
    -0.58
     Prosper
    -0.58
    POSITIVE LOGITS
     threw
    3.15
     tossed
    1.95
     throws
    1.92
     hurled
    1.82
     thrown
    1.74
     throw
    1.71
    Throw
    1.61
     throwing
    1.61
     tore
    1.60
     flung
    1.60
    Activations Density 0.018%

    No Known Activations