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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24383
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, such as software upgrades and code linking

    oai_token-act-pair · gpt-3.5-turbo

    references to links or connections within a digital or technological context

    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
     McCoy
    -0.81
     Yates
    -0.79
     Browns
    -0.76
     Beau
    -0.76
     bathrooms
    -0.76
     Beard
    -0.76
     Vul
    -0.75
    bath
    -0.72
     toilets
    -0.71
     Mint
    -0.71
    POSITIVE LOGITS
     link
    2.14
    link
    2.08
     Link
    1.94
    Link
    1.89
     links
    1.85
     LINK
    1.78
     linking
    1.78
    links
    1.78
     linkage
    1.74
     Links
    1.68
    Activations Density 0.259%

    No Known Activations