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

    Neuronpedia

    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. 8-RES-JB
    11. 4441
    Prev
    Next
    INDEX
    Explanations

    mentions of fake news and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "fake news" and misinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aird
    -0.75
     dues
    -0.75
    illes
    -0.72
    ktop
    -0.71
    atri
    -0.70
    onding
    -0.68
    foreseen
    -0.68
    airo
    -0.67
    anse
    -0.67
    emale
    -0.66
    POSITIVE LOGITS
    ument
    1.11
     disinformation
    1.02
     misinformation
    1.01
     propag
    1.00
     perpetrated
    1.00
     pedd
    0.98
     concoct
    0.97
     falsehood
    0.97
     nonsense
    0.95
     debunked
    0.93
    Activations Density 0.197%

    No Known Activations