© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 13871
    Prev
    Next
    INDEX
    Explanations

    the concept of comfort or being at ease

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comfort and feelings of being at ease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bard
    -0.82
    bey
    -0.72
    fleet
    -0.70
    hex
    -0.70
    */(
    -0.68
    eters
    -0.67
    vernment
    -0.66
    etheus
    -0.65
    GBT
    -0.65
    ificial
    -0.65
    POSITIVE LOGITS
    ably
    0.94
     enough
    0.85
     comfortable
    0.77
    ãĥ¼ãĥĨ
    0.71
    Medium
    0.68
    fortable
    0.68
     margins
    0.65
     +/-
    0.65
     Resident
    0.64
     intervals
    0.64
    Activations Density 0.014%

    No Known Activations