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. 2-RES-JB
    6. 5037
    Prev
    Next
    INDEX
    Explanations

    mentions of events or occasions

    oai_token-act-pair · gpt-3.5-turbo

    references to festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.75
    aundering
    -0.74
    bole
    -0.73
    dimensional
    -0.72
    hatt
    -0.71
    DonaldTrump
    -0.69
    enton
    -0.65
     dimensional
    -0.65
     charism
    -0.63
    cano
    -0.63
    POSITIVE LOGITS
    ivals
    1.32
     festival
    1.15
     festivals
    1.15
     Festival
    1.07
     Fest
    1.02
    Fest
    0.97
    é¾įå¥ij士
    0.91
    grounds
    0.78
     organisers
    0.76
     Weekend
    0.76
    Activations Density 0.013%

    No Known Activations