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. 14160
    Prev
    Next
    INDEX
    Explanations

    verbs related to physically reaching out and grabbing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grab" 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
    tti
    -0.75
    tics
    -0.70
    hemat
    -0.66
    llo
    -0.66
    inea
    -0.64
    ulo
    -0.63
    isf
    -0.61
    ^^
    -0.61
     Sabb
    -0.61
    sufficient
    -0.60
    POSITIVE LOGITS
     grab
    3.71
    grab
    2.50
     grabs
    2.42
     grabbing
    2.32
    Grab
    2.16
     Grab
    2.10
     grabbed
    1.83
     snag
    1.57
     snatch
    1.47
     steal
    1.23
    Activations Density 0.008%

    No Known Activations