© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific Twitter account related to Donald J. Trump

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Donald Trump and his social media handle

    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
    utic
    -0.74
     chilling
    -0.63
    ker
    -0.62
    pering
    -0.61
     Malays
    -0.61
     Hyundai
    -0.60
    lessly
    -0.59
    iencies
    -0.59
     Tec
    -0.59
    cer
    -0.59
    POSITIVE LOGITS
    Jr
    0.86
    realDonaldTrump
    0.79
    alsh
    0.74
    ocobo
    0.71
     surrogate
    0.71
    ometown
    0.67
    JD
    0.66
     Tweet
    0.65
    TRUMP
    0.65
    roud
    0.64
    Activations Density 0.025%

    No Known Activations