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. 2-RES-JB
    6. 24436
    Prev
    Next
    INDEX
    Explanations

    proper names of politicians

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orate
    -0.72
    istically
    -0.72
     Viking
    -0.67
    orous
    -0.66
     Jericho
    -0.65
    Brave
    -0.64
    istic
    -0.64
    toggle
    -0.64
    olithic
    -0.63
    othy
    -0.63
    POSITIVE LOGITS
     Wasserman
    1.15
     Schultz
    0.97
     Tanz
    0.92
    ignt
    0.81
    wcs
    0.74
    Leaks
    0.73
     nodd
    0.73
    borough
    0.72
    sheets
    0.72
    engers
    0.72
    Activations Density 0.006%

    No Known Activations