© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 22238
    Prev
    Next
    INDEX
    Explanations

    information related to government surveillance activities

    oai_token-act-pair · gpt-3.5-turbo

    references to secretive or classified governmental activities and related documents

    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
    áµ
    -0.64
    âĪ
    -0.59
    jj
    -0.59
     masc
    -0.58
    ciation
    -0.58
    entary
    -0.58
     ç¥ŀ
    -0.58
     Towns
    -0.57
    reci
    -0.56
    Ö
    -0.56
    POSITIVE LOGITS
     Wikileaks
    1.42
     WikiLeaks
    1.32
     blackmail
    1.32
     whistleblower
    1.29
    ileaks
    1.29
     incrim
    1.23
     dossier
    1.22
     espionage
    1.21
    NSA
    1.20
     whistlebl
    1.18
    Activations Density 0.989%

    No Known Activations