© 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. 9-RES-JB
    11. 16689
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by objects related to cooking or physical objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conom
    -0.74
    affe
    -0.70
    soDeliveryDate
    -0.69
    bats
    -0.68
    roid
    -0.66
    TPP
    -0.64
    acters
    -0.62
    FF
    -0.62
    urdue
    -0.62
    ikan
    -0.61
    POSITIVE LOGITS
    yx
    1.12
     top
    1.12
     behalf
    1.07
    erous
    1.03
     steroids
    0.99
    top
    0.97
    screen
    0.96
     occasion
    0.94
     display
    0.93
    etime
    0.92
    Activations Density 0.166%

    No Known Activations