© 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. 7-RES-JB
    11. 23812
    Prev
    Next
    INDEX
    Explanations

    the word "stealth" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stealth and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.77
    ICAN
    -0.74
    ONT
    -0.73
    ENTS
    -0.71
    artney
    -0.70
    onz
    -0.68
    ktop
    -0.63
    Interstitial
    -0.63
    ocese
    -0.62
    ¢
    -0.61
    POSITIVE LOGITS
    ily
    1.14
    ively
    1.00
    ibility
    0.97
    iest
    0.95
     camouflage
    0.94
     bomber
    0.91
    iness
    0.90
    door
    0.89
     stealth
    0.85
    y
    0.84
    Activations Density 0.041%

    No Known Activations