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. 0-RES-JB
    6. 21342
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "IU" followed by a single-digit value

    oai_token-act-pair · gpt-3.5-turbo

    references to Indiana University (IU)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.80
    sys
    -0.80
    flame
    -0.79
     Diesel
    -0.71
    hab
    -0.70
    fred
    -0.70
     ber
    -0.69
    Ń·
    -0.66
     Dresden
    -0.66
    essee
    -0.65
    POSITIVE LOGITS
     ng
    2.13
     IU
    2.10
     ov
    1.94
    IU
    1.80
     Ov
    1.25
     ovarian
    1.22
     Angular
    1.14
     Akin
    1.13
    MU
    1.13
     foll
    1.12
    Activations Density 0.053%

    No Known Activations