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. 8-RES-JB
    6. 16182
    Prev
    Next
    INDEX
    Explanations

    names of locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Rocky" and "Corey."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wich
    -0.90
    manship
    -0.86
    mble
    -0.85
    edin
    -0.85
    iya
    -0.82
    ively
    -0.80
    nown
    -0.79
    rett
    -0.79
    lich
    -0.76
    fully
    -0.76
    POSITIVE LOGITS
     Schwarzenegger
    0.78
     Cic
    0.71
    sson
    0.67
     Mig
    0.63
     Horror
    0.63
    anka
    0.62
     Herz
    0.61
     Dynam
    0.60
    izoph
    0.60
     Âł Âł
    0.60
    Activations Density 0.094%

    No Known Activations