© 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. 11-RES-JB
    11. 17066
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump and his plans to build a wall

    oai_token-act-pair · gpt-3.5-turbo

    references to building a wall and immigration policies associated with Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vic
    -0.79
     Hut
    -0.78
     Belg
    -0.78
     Desmond
    -0.76
    zai
    -0.74
    gaard
    -0.73
     Bam
    -0.73
     ILCS
    -0.73
     Leone
    -0.72
    adish
    -0.72
    POSITIVE LOGITS
     Trump
    1.35
    Trump
    1.29
    TRUMP
    1.26
     Melania
    1.17
     Apprentice
    1.17
     Ivanka
    1.17
     golf
    1.09
     Donald
    1.04
    Donald
    1.04
     TRUMP
    1.03
    Activations Density 0.483%

    No Known Activations