Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23418
    Prev
    Next
    INDEX
    Explanations

    terms related to government surveillance and intelligence activities

    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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rition
    -0.73
    iasis
    -0.68
     realism
    -0.67
     Dise
    -0.66
     redemption
    -0.65
     sculpt
    -0.64
     restoration
    -0.64
     Quantity
    -0.64
    Solution
    -0.63
     deficiency
    -0.63
    POSITIVE LOGITS
     communications
    1.08
     telephone
    1.05
     encrypted
    1.02
     phone
    1.02
     chats
    1.02
     Americans
    0.99
     Gmail
    0.97
     phones
    0.96
     citizens
    0.96
     foreigners
    0.96
    Activations Density 0.242%

    No Known Activations