© 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. 552
    Prev
    Next
    INDEX
    Explanations

    parentheses and numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dates in the format "(month year)" where the year is over 2000

    oai_token-act-pair · gpt-3.5-turbo
    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
     Bian
    -0.73
     tox
    -0.72
     Ferr
    -0.71
     Ku
    -0.68
     invari
    -0.68
     Kru
    -0.68
     Samar
    -0.67
     Trent
    -0.67
     imperson
    -0.65
     Rodney
    -0.65
    POSITIVE LOGITS
    MSN
    1.01
    ...)
    1.01
    5
    0.97
    3
    0.95
    needs
    0.93
    8
    0.92
    emphasis
    0.92
    1
    0.92
    12
    0.92
    2
    0.92
    Activations Density 0.050%

    No Known Activations