© 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. 8-RES-JB
    11. 7749
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references

    oai_token-act-pair · gpt-3.5-turbo

    significant dates, locations, and entities related to events or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assorted
    -0.60
    accompanied
    -0.57
    ãĥ©ãĥ³
    -0.56
     horm
    -0.55
    Magn
    -0.54
    MODE
    -0.52
     Arkham
    -0.52
    little
    -0.51
     Minority
    -0.51
    onomy
    -0.50
    POSITIVE LOGITS
     nor
    2.24
     anymore
    2.23
    nor
    1.52
     whatsoever
    1.39
     unless
    1.35
    yet
    1.31
     Nor
    1.17
     yet
    1.15
    unless
    1.14
     except
    1.09
    Activations Density 0.999%

    No Known Activations