© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 6656
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bullet."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bullet" in various contexts

    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
    wcsstore
    -0.72
    uthor
    -0.71
     volunt
    -0.68
     Suc
    -0.65
     Mistress
    -0.65
    noon
    -0.65
    hern
    -0.64
     Saud
    -0.64
     Clause
    -0.63
     facult
    -0.62
    POSITIVE LOGITS
    proof
    1.38
     holes
    1.02
     bullet
    0.97
     bullets
    0.94
     hole
    0.91
     dodged
    0.87
    guns
    0.82
    arding
    0.81
    ins
    0.81
     casing
    0.80
    Activations Density 0.034%

    No Known Activations