© 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. 2-RES-JB
    11. 18855
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fake" with strong activation

    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 @ 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
    xual
    -0.79
    hens
    -0.71
    CONCLUS
    -0.69
    ires
    -0.69
     Discuss
    -0.68
    arching
    -0.68
    quished
    -0.67
    ands
    -0.67
    Thom
    -0.66
    oran
    -0.65
    POSITIVE LOGITS
     fake
    0.94
     pas
    0.86
     Fake
    0.84
    Fake
    0.81
     phony
    0.80
    fake
    0.78
     bait
    0.76
    ²¾
    0.76
    ument
    0.76
     faked
    0.73
    Activations Density 0.017%

    No Known Activations