© 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. 11-RES-JB
    11. 5030
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How did you" or "How do you" related to personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    repeated questions directed at individuals regarding their experiences or actions

    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
     Skies
    -0.64
    Cra
    -0.64
     Presence
    -0.62
    hao
    -0.61
    ORN
    -0.59
    elight
    -0.59
    Reloaded
    -0.58
     implication
    -0.57
     Kau
    -0.56
    fee
    -0.56
    POSITIVE LOGITS
     fared
    1.11
     cope
    1.05
     reconcile
    1.02
     fare
    0.95
     coping
    0.95
     reconcil
    0.92
     handle
    0.88
     manage
    0.87
     pronounce
    0.86
     fares
    0.85
    Activations Density 0.105%

    No Known Activations