© 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. 17063
    Prev
    Next
    INDEX
    Explanations

    words related to physical comfort

    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 @ 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
    etheus
    -0.75
    natureconservancy
    -0.74
    degree
    -0.71
    Torrent
    -0.71
    sonian
    -0.71
    hire
    -0.68
    uscript
    -0.67
    chnology
    -0.66
    yss
    -0.65
    hibition
    -0.65
    POSITIVE LOGITS
     comfort
    1.10
     Comfort
    1.09
    comfort
    1.04
    ably
    0.85
    raints
    0.84
     cushion
    0.79
     margins
    0.78
    ãĥ¼ãĥĨ
    0.77
     blanket
    0.74
    iously
    0.69
    Activations Density 0.013%

    No Known Activations