© 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. 8-RES-JB
    11. 6802
    Prev
    Next
    INDEX
    Explanations

    words related to food preparation techniques, particularly sautéing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "sauces" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGTON
    -0.83
     Dragonbound
    -0.68
    etheless
    -0.67
     Jenner
    -0.64
     GOODMAN
    -0.61
    atically
    -0.61
    enegger
    -0.60
    ORED
    -0.59
    itarian
    -0.59
    姫
    -0.58
    POSITIVE LOGITS
    pling
    1.30
    ucer
    1.21
    plings
    1.14
    ven
    1.11
    vant
    1.09
    xon
    1.08
    ppy
    1.04
    pp
    1.01
    pping
    1.01
    plin
    0.99
    Activations Density 0.015%

    No Known Activations