© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    dates and specific events in sports

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" in various contexts related to sports or 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
    Allah
    -0.77
    ptin
    -0.76
     âĨij
    -0.71
    plin
    -0.71
    anse
    -0.66
    usercontent
    -0.65
    soDeliveryDate
    -0.64
    9999
    -0.63
    antha
    -0.63
    MIT
    -0.63
    POSITIVE LOGITS
     offense
    1.15
    etime
    1.12
     occasion
    1.08
     behalf
    1.06
     Saturday
    0.98
     Sunday
    0.96
     offence
    0.94
     defense
    0.90
     Friday
    0.90
     Thursday
    0.87
    Activations Density 0.074%

    No Known Activations