© 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. 20609
    Prev
    Next
    INDEX
    Explanations

    words related to a state of calmness

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to tranquility and emotional stability

    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
    bucks
    -0.72
    GAME
    -0.68
    Filename
    -0.67
    WD
    -0.64
    Leaks
    -0.60
     liar
    -0.60
    replace
    -0.59
    Downloadha
    -0.59
    filename
    -0.59
    GA
    -0.59
    POSITIVE LOGITS
     demeanor
    0.97
     composure
    0.96
     tranqu
    0.92
    ude
    0.91
     nerves
    0.89
     calm
    0.87
    ness
    0.87
     prevailed
    0.87
     calmed
    0.85
     contemplation
    0.84
    Activations Density 0.109%

    No Known Activations