© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific studies

    oai_token-act-pair · gpt-3.5-turbo

    references to research studies

    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
    fw
    -0.64
     Fiesta
    -0.61
     resonance
    -0.60
     Kyr
    -0.59
    vernment
    -0.59
    mr
    -0.57
     Woody
    -0.57
    cycl
    -0.57
    gc
    -0.56
    RAY
    -0.54
    POSITIVE LOGITS
     conducted
    1.03
     methodology
    0.88
    udo
    0.88
     findings
    0.87
     abroad
    0.84
     undertaken
    0.84
     published
    0.83
     subjects
    0.80
     Subjects
    0.78
     commissioned
    0.77
    Activations Density 0.056%

    No Known Activations