© 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 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. 6-RES-JB
    11. 12064
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically looking for "stein" as part of the name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Stein" and its variations in relation to a specific context or discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompan
    -0.83
    teenth
    -0.79
    icable
    -0.76
     millenn
    -0.75
    fortunately
    -0.74
    profits
    -0.73
    phis
    -0.71
    necess
    -0.71
    rises
    -0.70
    phas
    -0.70
    POSITIVE LOGITS
    stein
    1.19
    ers
    1.04
    er
    1.04
    itz
    0.94
    hardt
    0.93
    berg
    0.89
    enstein
    0.87
     Berman
    0.78
     Strauss
    0.77
    ering
    0.77
    Activations Density 0.019%

    No Known Activations