© 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. 0-RES-JB
    11. 1135
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bow"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "bow."

    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
     MSI
    -0.69
     certain
    -0.65
     Soph
    -0.63
     CentOS
    -0.62
     isol
    -0.62
     tenants
    -0.60
     Hann
    -0.60
     Scient
    -0.59
     MIN
    -0.58
    GROUP
    -0.58
    POSITIVE LOGITS
    bow
    4.62
    bows
    3.69
    Bow
    2.06
    sword
    1.68
     Bow
    1.47
     bow
    1.44
     Bows
    1.27
     bows
    1.26
    axe
    1.12
    gun
    1.07
    Activations Density 0.010%

    No Known Activations