© 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. 10-RES-JB
    11. 3036
    Prev
    Next
    INDEX
    Explanations

    chemical substances, drugs, and related items or actions

    oai_token-act-pair · gpt-3.5-turbo

    specific substances and ingredients, often in the context of food and chemicals

    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
    eatures
    -0.79
    ographers
    -0.70
    undown
    -0.67
    ittees
    -0.66
    ndra
    -0.65
    lihood
    -0.64
     Governments
    -0.63
    OF
    -0.60
     careers
    -0.59
    ategories
    -0.59
    POSITIVE LOGITS
     apiece
    0.95
     tubing
    0.90
     goodness
    0.89
     sandwic
    0.88
     powder
    0.82
     towels
    0.77
     dough
    0.76
     crammed
    0.76
     compressed
    0.74
     deposited
    0.73
    Activations Density 0.258%

    No Known Activations