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. 1257
    Prev
    Next
    INDEX
    Explanations

    keywords related to government surveillance and data collection

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government surveillance and privacy concerns

    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
    ukemia
    -0.70
     proverb
    -0.70
     coping
    -0.68
    reci
    -0.68
    erest
    -0.66
     EntityItem
    -0.65
    Solution
    -0.64
    CONCLUS
    -0.64
    cipline
    -0.63
    HY
    -0.63
    POSITIVE LOGITS
     encrypted
    1.03
     eaves
    1.00
     communications
    0.95
     phones
    0.93
     unwitting
    0.93
    encrypted
    0.90
     conversations
    0.89
     intercepted
    0.89
     transmissions
    0.89
     wiret
    0.89
    Activations Density 0.410%

    No Known Activations