© 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. 1-RES-JB
    11. 24232
    Prev
    Next
    INDEX
    Explanations

    words related to bows or bowing

    oai_token-act-pair · gpt-3.5-turbo

    references to bows and bowing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    helle
    -0.69
    andro
    -0.68
    advant
    -0.66
     Lauder
    -0.66
    occ
    -0.66
    Crime
    -0.66
    oral
    -0.65
     Milton
    -0.64
    andum
    -0.64
    ussen
    -0.64
    POSITIVE LOGITS
     bow
    1.36
     bows
    1.27
     arrow
    1.07
    wright
    1.04
    bows
    1.03
    bow
    0.95
     arrows
    0.90
     bowling
    0.90
    Bow
    0.85
    strings
    0.83
    Activations Density 0.004%

    No Known Activations