© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13714
    Prev
    Next
    INDEX
    Explanations

    references to specific historical events or experiments, particularly related to early scientific studies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific scientific experiments or historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyways
    -0.66
     nor
    -0.63
     anyway
    -0.61
    ãĥĥãĥī
    -0.59
     nonex
    -0.56
    DERR
    -0.56
    aspers
    -0.56
     depreciation
    -0.55
    igel
    -0.54
    ãĥ¼
    -0.54
    POSITIVE LOGITS
     illustrates
    1.31
     reveals
    1.21
     depicts
    1.20
     demonstrates
    1.17
     hangs
    1.10
     begins
    1.08
     concludes
    1.06
     reads
    1.06
     explores
    1.06
     unfolds
    1.05
    Activations Density 0.646%

    No Known Activations