Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4342
    Prev
    Next
    INDEX
    Explanations

    locations and actions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to law enforcement and security

    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
    izoph
    -0.65
    ãĥİ
    -0.60
     referen
    -0.58
    retty
    -0.57
     hindsight
    -0.56
    ÃĥÃĤ
    -0.53
    âĸ¬âĸ¬
    -0.53
     somet
    -0.52
    à©
    -0.50
    uable
    -0.50
    POSITIVE LOGITS
    .[
    1.13
    .
    1.10
    .''.
    1.08
    .''
    1.01
    .]
    1.01
    ."
    0.99
    ."[
    0.97
    .'
    0.89
    .,"
    0.88
    .)
    0.86
    Activations Density 0.988%

    No Known Activations