© 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. 17854
    Prev
    Next
    INDEX
    Explanations

    phrases related to discomfort or unease

    oai_token-act-pair · gpt-3.5-turbo

    discussions around discomfort and unpleasant feelings

    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
    ework
    -0.84
    glas
    -0.82
    sonian
    -0.82
    ramid
    -0.82
    ioch
    -0.79
    oled
    -0.79
    illet
    -0.78
    bard
    -0.78
    ardless
    -0.77
    ilts
    -0.76
    POSITIVE LOGITS
    lihood
    0.74
     neighbours
    0.73
     disadvant
    0.73
    nesses
    0.73
     flare
    0.73
     agitation
    0.71
     nuisance
    0.71
     uncomfortable
    0.71
     pse
    0.69
     plague
    0.69
    Activations Density 0.056%

    No Known Activations