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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19816
    Prev
    Next
    INDEX
    Explanations

    news articles or headlines

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "News" in various contexts

    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
    ught
    -0.77
     slee
    -0.73
    vernment
    -0.71
    phrine
    -0.69
     goddamn
    -0.69
    inished
    -0.68
    otent
    -0.68
    BuyableInstoreAndOnline
    -0.68
    ugh
    -0.67
     erect
    -0.66
    POSITIVE LOGITS
    News
    1.03
    letters
    1.00
    NEWS
    0.98
     Coverage
    0.90
    Reporting
    0.89
     Tycoon
    0.86
    orial
    0.86
     News
    0.85
     Articles
    0.83
    reader
    0.83
    Activations Density 0.037%

    No Known Activations