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. 1-RES-JB
    6. 6024
    Prev
    Next
    INDEX
    Explanations

    mentions of military service

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bomb
    -0.67
     Hots
    -0.63
    phrine
    -0.63
     Vers
    -0.62
     dotted
    -0.61
     Fro
    -0.61
     Bros
    -0.60
     Studio
    -0.60
    Maps
    -0.59
     Resist
    -0.59
    POSITIVE LOGITS
    dinand
    0.95
    lyak
    0.93
    aucuses
    0.91
     councill
    0.85
    emale
    0.81
    cffff
    0.79
     volunte
    0.78
    benefit
    0.77
    rifice
    0.77
    avement
    0.75
    Activations Density 0.029%

    No Known Activations