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. 12319
    Prev
    Next
    INDEX
    Explanations

    sections related to names and possibly locations, possibly related to historical or fantastical contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "ĩ" in the text

    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
    rette
    -0.78
    raviolet
    -0.75
     bluff
    -0.71
    fet
    -0.69
    ulative
    -0.68
    sett
    -0.68
     blender
    -0.67
     hottest
    -0.66
    faced
    -0.66
    ters
    -0.64
    POSITIVE LOGITS
    ĩ
    1.43
    ī
    1.21
    Į
    1.15
    ĥ
    1.09
    ĭ
    1.05
    į
    1.03
    Ĥ
    1.01
    Ùĩ
    1.00
    ا
    1.00
    Ø
    0.99
    Activations Density 0.003%

    No Known Activations