© 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. 11077
    Prev
    Next
    INDEX
    Explanations

    phrases related to research findings or studies

    oai_token-act-pair · gpt-3.5-turbo

    references to studies and research findings

    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
    lihood
    -0.72
    othe
    -0.71
    Lago
    -0.71
    ardi
    -0.69
    oya
    -0.66
    hunt
    -0.65
    ghazi
    -0.64
    lla
    -0.63
    vity
    -0.62
    onday
    -0.62
    POSITIVE LOGITS
     research
    1.07
     experts
    1.03
     researchers
    1.03
     new
    1.03
     scientists
    1.01
     study
    0.92
     findings
    0.92
    Researchers
    0.91
     newly
    0.90
     researcher
    0.89
    Activations Density 0.245%

    No Known Activations