© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    metadata information such as authors, editors, and credits

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and their contributions in texts

    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
     momentarily
    -0.85
    pload
    -0.80
     piv
    -0.76
     undercut
    -0.74
     stride
    -0.74
    etheless
    -0.73
     paraly
    -0.73
     temporarily
    -0.72
     fres
    -0.71
    acity
    -0.71
    POSITIVE LOGITS
     Unknown
    1.15
     Various
    1.04
     Cosponsors
    1.03
     Nil
    0.98
     None
    0.97
     Ernest
    0.93
     TBA
    0.92
     Juan
    0.92
     Cec
    0.89
     Richard
    0.89
    Activations Density 0.085%

    No Known Activations