© 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. 4-RES-JB
    11. 22065
    Prev
    Next
    INDEX
    Explanations

    phrases related to intelligence agencies and committees

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence committees and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loading
    -0.71
    anan
    -0.71
    LOAD
    -0.68
    nered
    -0.68
    ifiers
    -0.64
    coni
    -0.64
     Rowling
    -0.64
    days
    -0.63
    interstitial
    -0.63
    kw
    -0.62
    POSITIVE LOGITS
     Agency
    0.89
     Oversight
    0.86
     Intelligence
    0.85
    elligence
    0.80
    racuse
    0.72
     Accountability
    0.72
     Bureau
    0.72
     Corps
    0.72
     Surveillance
    0.72
     Labs
    0.71
    Activations Density 0.014%

    No Known Activations