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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 8822
    Prev
    Next
    INDEX
    Explanations

    words related to shooting or aiming

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to the action of shooting

    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
    ebook
    -0.72
    uria
    -0.68
    anse
    -0.65
    emonic
    -0.64
    Label
    -0.63
    éĸ
    -0.63
    STEP
    -0.63
    uthor
    -0.62
    undai
    -0.62
    å§«
    -0.62
    POSITIVE LOGITS
     hoops
    1.11
     galleries
    0.84
     lasers
    0.84
     holes
    0.83
     arrows
    0.82
    outs
    0.76
     gallery
    0.75
     flares
    0.75
     shoot
    0.73
    pointers
    0.72
    Activations Density 0.044%

    No Known Activations