© 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. 10-RES-JB
    6. 12429
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially focusing on their initials

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beware
    -0.64
    =-=-=-=-=-=-=-=-
    -0.61
     extraction
    -0.59
     wart
    -0.59
     opaque
    -0.59
    theless
    -0.59
     Thieves
    -0.58
    å§«
    -0.58
     mountainous
    -0.57
     syll
    -0.57
    POSITIVE LOGITS
    .,
    1.20
    .;
    0.98
    .,"
    0.97
    isner
    0.95
    .:
    0.91
    .),
    0.89
    ./
    0.87
    .
    0.86
    ._
    0.85
     Abrams
    0.83
    Activations Density 0.079%

    No Known Activations