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. 4-RES-JB
    6. 23269
    Prev
    Next
    INDEX
    Explanations

    references to U.S. involvement or activities in global military or political situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States in various contexts

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

    No Comments

    Negative Logits
     Noir
    -0.96
     Siren
    -0.75
     Preferred
    -0.72
     Bach
    -0.69
     Pioneer
    -0.68
     Attribution
    -0.68
     CPC
    -0.67
     Siberian
    -0.67
     Siberia
    -0.67
     Syndicate
    -0.67
    POSITIVE LOGITS
    prising
    1.25
    nexpected
    1.13
    NA
    1.04
    seless
    1.04
    lyss
    0.99
    pperc
    0.97
    zbek
    0.91
    DP
    0.91
    topia
    0.91
    pport
    0.90
    Activations Density 0.053%

    No Known Activations