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. 7-RES-JB
    6. 20281
    Prev
    Next
    INDEX
    Explanations

    requests or tips indicated by the phrase "Have a tip we should know?"

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or requests for tips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zek
    -0.70
    alog
    -0.69
     largeDownload
    -0.68
    bourne
    -0.68
    uras
    -0.66
    eval
    -0.65
    etts
    -0.65
     Hann
    -0.64
    walk
    -0.63
     dracon
    -0.63
    POSITIVE LOGITS
    iframe
    0.82
     Spons
    0.74
    Semitism
    0.72
     donor
    0.71
    NPR
    0.70
     journalism
    0.70
    Subscribe
    0.67
     sponsoring
    0.66
     donors
    0.66
    Privacy
    0.65
    Activations Density 0.157%

    No Known Activations