© 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. 10691
    Prev
    Next
    INDEX
    Explanations

    words related to secrecy

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to secrecy and concealment

    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
    ergy
    -0.80
    Interstitial
    -0.77
    ermanent
    -0.72
    anza
    -0.71
    Demand
    -0.69
    Stars
    -0.68
    alian
    -0.68
    enegger
    -0.66
    ucc
    -0.66
    annis
    -0.65
    POSITIVE LOGITS
    recy
    1.10
     secrecy
    0.96
     shrouded
    0.95
    rets
    0.91
     shroud
    0.87
     secrets
    0.83
     secretive
    0.81
     secret
    0.80
    ariat
    0.79
     cloaked
    0.77
    Activations Density 0.008%

    No Known Activations