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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15275
    Prev
    Next
    INDEX
    Explanations

    mentions or tags related to the Twitter account @realDonaldTrump

    oai_token-act-pair · gpt-3.5-turbo

    references to the Twitter account of Donald Trump

    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
    lessly
    -0.81
     Tec
    -0.80
     Scandinavian
    -0.72
    vol
    -0.68
    ced
    -0.66
     Tek
    -0.65
     Abyssal
    -0.65
     Constantin
    -0.63
     Tel
    -0.63
     Dh
    -0.63
    POSITIVE LOGITS
    realDonaldTrump
    1.09
     surrogate
    0.89
    dinand
    0.89
     impeachment
    0.85
    TRUMP
    0.84
    cffff
    0.81
    clinton
    0.78
    espie
    0.77
     TRUMP
    0.77
    rison
    0.76
    Activations Density 0.008%

    No Known Activations