© 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. 0-RES-JB
    11. 11497
    Prev
    Next
    INDEX
    Explanations

    references to the former US President, Donald Trump

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Donald Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.75
    inis
    -0.70
    ³³³³³³³³³³³³³³³³
    -0.69
    CI
    -0.69
    ³³³
    -0.69
    ↵Âł
    -0.69
    inet
    -0.68
     cylinders
    -0.68
    -->
    -0.67
    ³³³³
    -0.66
    POSITIVE LOGITS
     Trump
    3.50
    Trump
    3.19
     TRUMP
    2.80
    TRUMP
    2.53
    trump
    2.42
     Donald
    2.19
    DonaldTrump
    2.09
    realDonaldTrump
    2.08
     Ivanka
    2.07
     Obama
    1.96
    Activations Density 0.064%

    No Known Activations