Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 4515
    Prev
    Next
    INDEX
    Explanations

    mentions of the broadcaster CBC

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 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
    wagen
    -1.01
    jury
    -0.82
    erva
    -0.74
    gered
    -0.71
    anmar
    -0.70
     Whedon
    -0.69
    erville
    -0.67
    warm
    -0.67
    emaker
    -0.66
    chest
    -0.66
    POSITIVE LOGITS
     News
    1.15
    NEWS
    1.12
    News
    1.01
     Archives
    0.93
    news
    0.92
     Radio
    0.89
     Newsp
    0.88
     Television
    0.85
    OM
    0.84
    CBC
    0.82
    Activations Density 0.025%

    No Known Activations