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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 609
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental and intelligence agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental organizations and agencies

    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
    natureconservancy
    -0.78
     Parables
    -0.71
     Kathleen
    -0.69
    ModLoader
    -0.68
    Fest
    -0.67
    nect
    -0.67
    bernatorial
    -0.66
     Twain
    -0.65
     Booker
    -0.65
    brainer
    -0.65
    POSITIVE LOGITS
     intelligence
    1.56
     spy
    1.55
     KGB
    1.52
     spies
    1.46
     espionage
    1.45
    intelligence
    1.44
     spying
    1.40
    CHQ
    1.33
     Intelligence
    1.31
     eaves
    1.28
    Activations Density 0.410%

    No Known Activations