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. 3-RES-JB
    6. 14083
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Huckabee"

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uscript
    -0.73
    ority
    -0.69
    âĶĢâĶĢ
    -0.68
    ition
    -0.65
    venge
    -0.64
    ivity
    -0.64
    ivities
    -0.63
     Cruiser
    -0.62
    女
    -0.61
    arial
    -0.60
    POSITIVE LOGITS
     Huckabee
    1.29
     Sanders
    0.85
     Santorum
    0.79
    enstein
    0.78
    weed
    0.78
    anne
    0.77
     Evans
    0.76
    lington
    0.75
     Pence
    0.73
     Caucus
    0.72
    Activations Density 0.009%

    No Known Activations