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. 0-RES-JB
    6. 3740
    Prev
    Next
    INDEX
    Explanations

    mentions of the news agency "Reuters."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Reuters" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.70
    ooth
    -0.70
    ee
    -0.67
    aun
    -0.65
     plat
    -0.63
    eer
    -0.62
    Cast
    -0.61
    opl
    -0.61
    ige
    -0.60
    disc
    -0.60
    POSITIVE LOGITS
     Reuters
    3.67
    Reuters
    2.23
     REUTERS
    2.11
     AFP
    1.85
     CNBC
    1.58
     Bloomberg
    1.57
     Getty
    1.49
    AFP
    1.48
     Politico
    1.47
    Bloomberg
    1.38
    Activations Density 0.012%

    No Known Activations