© 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. 9-RES-JB
    11. 5580
    Prev
    Next
    INDEX
    Explanations

    versions or variations of something

    oai_token-act-pair · gpt-3.5-turbo

    references to different versions of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤī
    -0.78
    redo
    -0.76
    usters
    -0.75
    ratulations
    -0.64
    veyard
    -0.64
     charism
    -0.64
    row
    -0.63
    inguished
    -0.63
    wealth
    -0.62
    inently
    -0.62
    POSITIVE LOGITS
     thereof
    1.23
     of
    0.94
     version
    0.77
     versions
    0.72
     numbering
    0.71
    UID
    0.71
    lihood
    0.67
    Versions
    0.66
    esan
    0.66
    etting
    0.65
    Activations Density 0.048%

    No Known Activations