© 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. 7-RES-JB
    11. 21173
    Prev
    Next
    INDEX
    Explanations

    instances of the term "fake news" with varying emphases

    oai_token-act-pair · gpt-3.5-turbo

    references to "fake news" and related criticisms of media credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.86
    artney
    -0.83
    aird
    -0.82
    illes
    -0.79
    onding
    -0.74
    atal
    -0.74
    foreseen
    -0.73
    union
    -0.73
    cise
    -0.72
    enture
    -0.71
    POSITIVE LOGITS
     misinformation
    1.07
     disinformation
    1.04
    ument
    1.04
     falsehood
    1.01
     debunk
    0.97
     debunked
    0.96
     perpetrated
    0.95
    False
    0.94
     propag
    0.90
     nonsense
    0.89
    Activations Density 0.234%

    No Known Activations