© 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. 10215
    Prev
    Next
    INDEX
    Explanations

    phrases related to espionage and intrigue

    oai_token-act-pair · gpt-3.5-turbo

    references to espionage or intelligence-related activities

    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
    cture
    -0.59
     Statement
    -0.59
     autobiography
    -0.58
     Proposition
    -0.58
     Phase
    -0.57
     Comprehensive
    -0.55
     Daylight
    -0.55
     graduation
    -0.54
     airspace
    -0.54
     biography
    -0.53
    POSITIVE LOGITS
    arers
    1.44
    achers
    1.38
    erers
    1.38
    casters
    1.35
    runners
    1.34
    makers
    1.34
    keepers
    1.33
    ists
    1.32
    agers
    1.31
    lers
    1.30
    Activations Density 0.723%

    No Known Activations