Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7915
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump and related political events

    oai_token-act-pair · gpt-3.5-turbo

    references to political statements and events involving Donald Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.47
    teness
    -0.44
     mages
    -0.42
    ont
    -0.42
    andom
    -0.42
    etically
    -0.42
    laughs
    -0.41
    opl
    -0.41
    --+
    -0.41
     linear
    -0.39
    POSITIVE LOGITS
     Cosponsors
    0.65
    glers
    0.60
    hower
    0.58
    osponsors
    0.57
     sponsoring
    0.55
     DOJ
    0.53
    issued
    0.52
    schild
    0.52
    Democrats
    0.50
     NAFTA
    0.50
    Activations Density 6.621%

    No Known Activations