© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    food-related terms such as dishes and flavors

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to food, music, crime, and emotional states

    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
    ucc
    -0.69
    lear
    -0.64
    ivism
    -0.63
    culture
    -0.59
    kus
    -0.59
    ivist
    -0.59
    olog
    -0.59
    士
    -0.58
    lopp
    -0.58
    psons
    -0.58
    POSITIVE LOGITS
     respectively
    0.72
     Hots
    0.68
     bordering
    0.63
     preceded
    0.62
     unheard
    0.60
     apiece
    0.60
     Leilan
    0.60
     followed
    0.58
    *.
    0.58
     flanked
    0.57
    Activations Density 0.546%

    No Known Activations