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. 10-RES-JB
    6. 15389
    Prev
    Next
    INDEX
    Explanations

    references to famous people, especially those known for their appearances and public lives

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrity culture and fashion

    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
     Chomsky
    -1.04
     Cato
    -0.81
     ATF
    -0.80
    termination
    -0.79
     Firearms
    -0.76
     mitigation
    -0.75
    lethal
    -0.74
    Unix
    -0.73
     systemd
    -0.73
     Tactical
    -0.72
    POSITIVE LOGITS
     bikini
    1.67
     actresses
    1.52
     nude
    1.49
     Beauty
    1.47
    Girls
    1.43
     dresses
    1.43
     sexy
    1.41
     princess
    1.40
    Beaut
    1.39
     beauty
    1.39
    Activations Density 0.736%

    No Known Activations