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. 9-RES-JB
    6. 12873
    Prev
    Next
    INDEX
    Explanations

    web sources embedded in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific institutions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.83
    cffff
    -0.80
     metic
    -0.76
     Klux
    -0.74
    uminati
    -0.74
    querade
    -0.73
    conservancy
    -0.71
     ende
    -0.69
    interstitial
    -0.69
     chimpanzees
    -0.68
    POSITIVE LOGITS
    Requires
    0.80
    reviewed
    0.79
    cdn
    0.71
    Topic
    0.71
     Featuring
    0.71
     Edited
    0.67
    girl
    0.67
     IMAGES
    0.65
    Available
    0.65
     VIEW
    0.64
    Activations Density 0.345%

    No Known Activations