© 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. 10-RES-JB
    11. 13867
    Prev
    Next
    INDEX
    Explanations

    numbered lists or sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to sports 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
     compliant
    -0.56
    enegger
    -0.54
    ¢
    -0.53
     alternatives
    -0.53
    aware
    -0.52
    eware
    -0.52
    recy
    -0.51
     substitutes
    -0.51
    icient
    -0.51
    oppable
    -0.51
    POSITIVE LOGITS
     semester
    0.90
     season
    0.86
     week
    0.86
     episode
    0.85
     playthrough
    0.85
     Week
    0.84
     Wrestle
    0.84
     weekend
    0.81
     halftime
    0.78
     inning
    0.78
    Activations Density 0.663%

    No Known Activations