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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17046
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'sa' with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sa," indicating a focus on the concept of seasoning or flavoring

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

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.84
    INGTON
    -0.82
    enegger
    -0.76
    hips
    -0.74
    itarian
    -0.72
    etheless
    -0.69
    ãĥ¯ãĥ³
    -0.69
    hyde
    -0.68
    姫
    -0.67
    LIN
    -0.66
    POSITIVE LOGITS
    pling
    1.23
    ven
    1.08
    plings
    1.00
    uth
    1.00
    arin
    0.98
    ucer
    0.98
    llan
    0.97
    ppy
    0.96
    uten
    0.95
    pp
    0.93
    Activations Density 0.006%

    No Known Activations