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. 7-RES-JB
    6. 740
    Prev
    Next
    INDEX
    Explanations

    information related to show premieres, releases, and details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of media availability and release details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.93
    zsche
    -0.78
    vati
    -0.77
    conservancy
    -0.75
    rious
    -0.75
     crem
    -0.69
    rous
    -0.69
    bek
    -0.69
     quo
    -0.68
    thy
    -0.66
    POSITIVE LOGITS
     theaters
    1.21
    DVD
    1.13
     paperback
    1.11
     Kindle
    1.10
     ebook
    1.09
     iTunes
    1.01
     DRM
    1.01
     theat
    1.00
     DVD
    1.00
     formats
    0.99
    Activations Density 0.848%

    No Known Activations