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. 9-RES-JB
    6. 22288
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms related to media, politics, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to elections and local events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cells
    -0.83
    BuyableInstoreAndOnline
    -0.81
    ilk
    -0.79
     Slater
    -0.78
    \-
    -0.76
     Phill
    -0.74
     Bulgar
    -0.73
    phys
    -0.72
    cffff
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    POSITIVE LOGITS
     event
    1.08
     trial
    1.04
     episode
    1.02
     announcement
    0.95
     campaign
    0.95
     election
    0.94
     showdown
    0.94
     finale
    0.92
     expedition
    0.91
     tournament
    0.90
    Activations Density 0.439%

    No Known Activations