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

    Neuronpedia

    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. 8-RES-JB
    11. 17813
    Prev
    Next
    INDEX
    Explanations

    ingredients used in cooking

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific ingredients or food-related terms

    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
    jriwal
    -0.76
    govtrack
    -0.67
    tumblr
    -0.67
    ufact
    -0.64
    akeru
    -0.62
     elector
    -0.61
     avail
    -0.61
    oola
    -0.59
    £ı
    -0.59
    atform
    -0.59
    POSITIVE LOGITS
    utsche
    0.87
    egu
    0.64
    ãĤ£
    0.63
    oxide
    0.62
    alog
    0.62
    aternity
    0.61
    uction
    0.61
    Secure
    0.61
    rouse
    0.60
    Override
    0.60
    Activations Density 0.531%

    No Known Activations