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. 0-RES-JB
    6. 768
    Prev
    Next
    INDEX
    Explanations

    words related to surveillance or monitoring

    oai_token-act-pair · gpt-3.5-turbo

    mentions of surveillance or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minotaur
    -0.64
     juveniles
    -0.63
     Ale
    -0.62
     symbol
    -0.62
     rye
    -0.61
     Nig
    -0.60
     Cup
    -0.59
     Centauri
    -0.59
     associate
    -0.59
     LB
    -0.59
    POSITIVE LOGITS
    sur
    4.17
    Sur
    2.06
     Sur
    1.71
     SUR
    1.44
    swing
    1.37
     sur
    1.30
     Surve
    1.21
     unsur
    1.12
     Surge
    1.11
    shock
    1.10
    Activations Density 0.009%

    No Known Activations