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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19087
    Prev
    Next
    INDEX
    Explanations

    food-related words and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    food-related terminology and descriptions

    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
    htaking
    -0.58
     virginity
    -0.57
     precisely
    -0.57
     NEVER
    -0.55
    osate
    -0.54
     hardly
    -0.52
    ãĥ¯ãĥ³
    -0.52
    0000000000000000
    -0.51
    DonaldTrump
    -0.51
     EVERY
    -0.50
    POSITIVE LOGITS
    cellaneous
    0.68
     other
    0.65
     others
    0.63
     afterward
    0.62
    Other
    0.59
     else
    0.57
    other
    0.56
    Later
    0.56
     Others
    0.55
     Other
    0.55
    Activations Density 1.030%

    No Known Activations