© 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. 4-RES-JB
    11. 10195
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements of food-related items such as kilograms and grams

    oai_token-act-pair · gpt-3.5-turbo

    measurements of food consumption

    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
    ::::::::
    -0.64
    bred
    -0.62
    ties
    -0.61
    redo
    -0.60
    print
    -0.58
    otto
    -0.58
     favor
    -0.57
     antit
    -0.57
     Caesar
    -0.56
    anim
    -0.55
    POSITIVE LOGITS
    osuke
    0.89
     apiece
    0.74
     increments
    0.73
    poons
    0.70
     Ibid
    0.69
    avin
    0.67
    /$
    0.67
    ilty
    0.67
    ).[
    0.65
     respectively
    0.65
    Activations Density 0.228%

    No Known Activations