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. 3-RES-JB
    6. 14588
    Prev
    Next
    INDEX
    Explanations

    references to the Canadian Broadcasting Corporation (CBC)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the CBC (Canadian Broadcasting Corporation)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.83
    kus
    -0.77
    erva
    -0.75
    atra
    -0.72
    icio
    -0.71
    é¾įå
    -0.66
    lopp
    -0.65
    chest
    -0.65
    gets
    -0.64
    hots
    -0.64
    POSITIVE LOGITS
    CBC
    1.16
     CBC
    1.08
     Theatre
    0.80
     Municip
    0.77
    CTV
    0.75
     Scotia
    0.74
    RC
    0.74
    NEWS
    0.74
     Broadcasting
    0.73
     Broadcast
    0.72
    Activations Density 0.008%

    No Known Activations