© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17037
    Prev
    Next
    INDEX
    Explanations

    keywords related to news sources and news content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news within various contexts

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

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.69
    asse
    -0.69
     Scher
    -0.67
    sei
    -0.67
    orsi
    -0.65
    qqa
    -0.65
    ength
    -0.65
     grun
    -0.65
    ceived
    -0.63
    ayne
    -0.63
    POSITIVE LOGITS
    worthy
    1.02
    feed
    1.01
    room
    0.97
    reader
    0.97
    orial
    0.95
    worthiness
    0.91
    rooms
    0.88
    flash
    0.85
     headlines
    0.82
    blog
    0.78
    Activations Density 0.036%

    No Known Activations