© 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. 10-RES-JB
    11. 23308
    Prev
    Next
    INDEX
    Explanations

    food-related words, specifically related to macaroni and cheese

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "mac" and "sy" related concepts, possibly related to food and psychological themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PORT
    -0.77
     Doe
    -0.74
     Richards
    -0.72
    Ell
    -0.71
    INGTON
    -0.70
    IDES
    -0.70
    channelAvailability
    -0.69
     Falls
    -0.67
    ORED
    -0.66
    River
    -0.66
    POSITIVE LOGITS
    ocular
    1.04
    estones
    0.85
    enaries
    0.85
    iddling
    0.84
    ocobo
    0.82
    coon
    0.81
    ework
    0.80
    ineries
    0.80
    itudes
    0.80
    glers
    0.77
    Activations Density 0.133%

    No Known Activations