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. 22514
    Prev
    Next
    INDEX
    Explanations

    references to the Canadian Prime Minister, Justin Trudeau

    oai_token-act-pair · gpt-3.5-turbo

    references to Justin Trudeau

    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
    bler
    -0.83
    gran
    -0.75
    oxide
    -0.73
    Ö¼
    -0.73
    âĵĺ
    -0.73
    76561
    -0.72
    ×Ļ
    -0.70
    iHUD
    -0.67
    stract
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
    udeau
    1.22
     Trudeau
    1.10
     Jinping
    0.80
    bourg
    0.79
    ité
    0.78
    isms
    0.76
     Liberals
    0.76
    ism
    0.75
    utan
    0.74
     ministerial
    0.72
    Activations Density 0.011%

    No Known Activations