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. 1-RES-JB
    6. 16571
    Prev
    Next
    INDEX
    Explanations

    dates, particularly related to events like inaugurations

    oai_token-act-pair · gpt-3.5-turbo

    references to the month of August

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BO
    -0.76
     Hearts
    -0.66
    Premium
    -0.66
     Plasma
    -0.66
     Panic
    -0.63
    Heat
    -0.62
     dish
    -0.62
     uninsured
    -0.61
    Standard
    -0.60
     Origin
    -0.59
    POSITIVE LOGITS
    aug
    1.15
    sburg
    1.15
    urated
    1.13
    uration
    1.13
    urations
    1.06
    ruary
    0.98
    uary
    0.97
    sburgh
    0.95
    roup
    0.94
    erville
    0.92
    Activations Density 0.005%

    No Known Activations