© 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. 19988
    Prev
    Next
    INDEX
    Explanations

    the term "stalwart" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to stalemate situations, particularly in historical or competitive 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
    yre
    -0.76
    ramid
    -0.75
     Simulator
    -0.74
    orate
    -0.70
    hy
    -0.67
     Agency
    -0.66
    consumer
    -0.64
     Loans
    -0.63
     Nationwide
    -0.63
     Behavior
    -0.63
    POSITIVE LOGITS
     stal
    1.53
    emate
    1.33
    wart
    1.25
    warts
    1.18
     horizont
    0.95
    stal
    0.90
    eness
    0.81
     pend
    0.78
    staff
    0.78
     incumb
    0.72
    Activations Density 0.006%

    No Known Activations