© 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. 2-RES-JB
    11. 968
    Prev
    Next
    INDEX
    Explanations

    words that start with "sa"

    oai_token-act-pair · gpt-4-turbo

    instances of the word "sa" followed by a suffix

    oai_token-act-pair · gpt-3.5-turbo

    references to "sauces" or "saucing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.80
    INGTON
    -0.78
    LIN
    -0.74
    enegger
    -0.73
    hyde
    -0.72
    姫
    -0.72
    itarian
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.68
     Mortal
    -0.67
    DragonMagazine
    -0.66
    POSITIVE LOGITS
    pling
    1.08
    ven
    1.01
    uten
    0.99
    arin
    0.97
    uth
    0.94
    llan
    0.92
    plings
    0.89
    ucer
    0.88
    uter
    0.86
     sa
    0.85
    Activations Density 0.007%

    No Known Activations