© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19423
    Prev
    Next
    INDEX
    Explanations

    mentions of significant global events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and other high-frequency function words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     besides
    -0.72
     namely
    -0.68
    ibl
    -0.62
    !.
    -0.59
     whilst
    -0.58
    !!
    -0.58
    *.
    -0.57
     owing
    -0.57
    !!!
    -0.56
    ambo
    -0.56
    POSITIVE LOGITS
     nation
    1.00
     same
    0.99
     latter
    0.97
    resa
    0.95
     Clintons
    0.93
     slightest
    0.90
     latest
    0.90
     United
    0.90
     Kremlin
    0.89
     toughest
    0.88
    Activations Density 1.064%

    No Known Activations