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. 3-RES-JB
    6. 10321
    Prev
    Next
    INDEX
    Explanations

    mentions of ammunition rounds

    oai_token-act-pair · gpt-3.5-turbo

    references to specific quantities or measures related to rounds of ammunition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.68
    WN
    -0.65
    uras
    -0.64
    natureconservancy
    -0.64
     Cald
    -0.62
    âĹ¼
    -0.61
    minist
    -0.61
    rians
    -0.60
    oir
    -0.59
    Alabama
    -0.59
    POSITIVE LOGITS
     rounds
    0.89
    amples
    0.87
    umenthal
    0.78
    hift
    0.78
    ounds
    0.77
     Rounds
    0.77
    oldown
    0.75
    uggest
    0.75
    krit
    0.75
    mith
    0.74
    Activations Density 0.009%

    No Known Activations