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. 19219
    Prev
    Next
    INDEX
    Explanations

    references to intelligence agencies from around the world

    oai_token-act-pair · gpt-3.5-turbo

    key entities and organizations related to intelligence and surveillance

    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
     healthier
    -0.78
    amaz
    -0.78
    galitarian
    -0.77
    Whe
    -0.76
     bicycl
    -0.75
     ç¥ŀ
    -0.74
    ð
    -0.72
    Owner
    -0.71
    clus
    -0.70
     MLA
    -0.68
    POSITIVE LOGITS
     spy
    1.64
     spies
    1.62
     espionage
    1.61
     spying
    1.57
     KGB
    1.55
     covert
    1.47
     intelligence
    1.41
    ionage
    1.41
    CIA
    1.39
     CIA
    1.35
    Activations Density 0.824%

    No Known Activations