© 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. 3435
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific time periods or events within a schedule

    oai_token-act-pair · gpt-3.5-turbo

    terms related to seasons and timeframes in sports and events

    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
    rather
    -0.63
    $.
    -0.62
    SAY
    -0.61
     trusting
    -0.59
    pees
    -0.58
    lying
    -0.58
    INST
    -0.58
    agree
    -0.57
    who
    -0.57
    rir
    -0.57
    POSITIVE LOGITS
     looms
    1.30
     begins
    1.24
     coincides
    1.16
     lasted
    1.15
     coincided
    1.15
     ended
    1.11
     starts
    1.10
     lasts
    1.08
     brings
    1.07
     airs
    1.07
    Activations Density 0.347%

    No Known Activations