© 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. 20856
    Prev
    Next
    INDEX
    Explanations

    phrases related to written publications like blog posts, letters, statements, and tweets

    oai_token-act-pair · gpt-3.5-turbo

    documents and written communications, particularly blog posts and letters

    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
    cause
    -0.77
    "},"
    -0.63
    ãĤ¦ãĤ¹
    -0.61
    $.
    -0.61
    depend
    -0.60
    levels
    -0.60
    inges
    -0.58
    wings
    -0.57
    alions
    -0.57
     reservoirs
    -0.56
    POSITIVE LOGITS
     published
    0.93
     titled
    0.91
     released
    0.91
     dated
    0.90
     accompanying
    0.85
     obtained
    0.83
     posted
    0.79
     entitled
    0.77
     reviewed
    0.75
     submitted
    0.74
    Activations Density 0.217%

    No Known Activations