© 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. 0-RES-JB
    11. 5390
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical comfort, such as "comfort," "comforted," and "comforting."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disks
    -0.66
    ern
    -0.65
     Lic
    -0.65
     Levin
    -0.65
    edin
    -0.64
     Seeds
    -0.62
     Mush
    -0.62
    rd
    -0.60
    ids
    -0.60
    inator
    -0.60
    POSITIVE LOGITS
     comfort
    4.17
    comfort
    2.56
     Comfort
    2.35
     consolation
    1.70
     comforting
    1.68
    forts
    1.48
     convenience
    1.38
     comfortable
    1.33
     warmth
    1.31
     discomfort
    1.28
    Activations Density 0.004%

    No Known Activations