© 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 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. 3212
    Prev
    Next
    INDEX
    Explanations

    dates or times of planned events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the start of events or actions

    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
    uably
    -0.90
    aths
    -0.79
    itably
    -0.75
    icons
    -0.74
    icator
    -0.68
    warts
    -0.68
    acco
    -0.67
    idated
    -0.66
    particularly
    -0.65
    ingly
    -0.65
    POSITIVE LOGITS
     airing
    1.22
     accepting
    0.94
     raining
    0.93
     arriving
    0.93
     anew
    0.90
     filming
    0.88
     circulating
    0.87
     operations
    0.86
     receiving
    0.85
     rolling
    0.85
    Activations Density 0.102%

    No Known Activations