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. 9-RES-JB
    6. 11745
    Prev
    Next
    INDEX
    Explanations

    statements or sentences where something "makes sense"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating logical coherence or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.70
     downed
    -0.62
    ching
    -0.62
    pi
    -0.61
     repaired
    -0.61
     laun
    -0.61
    idency
    -0.59
     resultant
    -0.59
    eger
    -0.58
    kee
    -0.58
    POSITIVE LOGITS
    DragonMagazine
    0.82
    é¾įå¥ij士
    0.79
     partName
    0.78
     logically
    0.77
     why
    0.76
    SourceFile
    0.72
     WHY
    0.72
    nw
    0.70
    éĸ
    0.69
     considering
    0.69
    Activations Density 0.031%

    No Known Activations