© 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. 11-RES-JB
    6. 2420
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "new" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    references to new products, campaigns, or initiatives

    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
    ammers
    -0.83
    ENTS
    -0.79
    aunts
    -0.73
    lees
    -0.70
    these
    -0.70
    ifles
    -0.70
    WARE
    -0.70
    Changes
    -0.68
    acers
    -0.68
    urations
    -0.67
    POSITIVE LOGITS
    bie
    1.23
     generation
    1.09
     era
    0.99
     breed
    0.96
     batch
    0.94
     chapter
    0.91
    foundland
    0.91
     iteration
    0.91
     incarnation
    0.90
     edition
    0.90
    Activations Density 0.081%

    No Known Activations