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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9160
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Trump"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Trump."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANA
    -0.69
    BILITY
    -0.69
     ASA
    -0.69
     Austral
    -0.69
     Mortal
    -0.68
    iencies
    -0.68
     Celt
    -0.67
     [|
    -0.67
    PsyNetMessage
    -0.66
     CentOS
    -0.66
    POSITIVE LOGITS
    care
    0.95
    Trump
    0.93
    TRUMP
    0.89
     Donald
    0.86
     Trump
    0.86
     supporters
    0.82
    Care
    0.79
     impeachment
    0.78
    ovich
    0.77
    donald
    0.77
    Activations Density 0.053%

    No Known Activations