© 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. 6-RES-JB
    11. 9267
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by "MORE" which might indicate the emphasis on something specific in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "MORE" in different contexts

    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
    ãĥ¼ãĥĨãĤ£
    -0.81
    ãĤ©
    -0.78
     Columb
    -0.72
     eg
    -0.68
    ãĥ¥
    -0.66
    ãĥĨãĤ£
    -0.65
    asus
    -0.64
    ãĤ£
    -0.62
    Filename
    -0.59
    ãĤ¬
    -0.58
    POSITIVE LOGITS
     VIDEOS
    0.77
    enthal
    0.75
    enegger
    0.73
    iciary
    0.70
    uchin
    0.69
    ellen
    0.69
     Jr
    0.66
    eller
    0.65
    eat
    0.64
    PP
    0.64
    Activations Density 0.019%

    No Known Activations