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. 6233
    Prev
    Next
    INDEX
    Explanations

    political party names, particularly focusing on the Social Democrats

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties, specifically Social Democrats and Liberal Democrats

    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
     Whitney
    -0.75
     Nationwide
    -0.72
    inventoryQuantity
    -0.72
     Dull
    -0.68
     Webster
    -0.67
     FAA
    -0.66
     McMahon
    -0.64
     Garn
    -0.63
    depending
    -0.63
     Compton
    -0.63
    POSITIVE LOGITS
    alion
    0.88
     Orchestra
    0.79
     Syndicate
    0.74
     rebels
    0.74
    astery
    0.74
    alions
    0.73
     paramilitary
    0.69
     Movement
    0.69
    ariat
    0.69
    ieties
    0.67
    Activations Density 0.072%

    No Known Activations