© 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. 7-RES-JB
    11. 12625
    Prev
    Next
    INDEX
    Explanations

    emotions or sensations related to feelings of various intensities

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to feelings and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Camer
    -0.78
    photos
    -0.63
    angle
    -0.62
     Agricultural
    -0.62
     Accounting
    -0.61
     Correspond
    -0.61
    adish
    -0.61
     Display
    -0.59
     Landing
    -0.59
    PHOTOS
    -0.58
    POSITIVE LOGITS
     comfortable
    1.03
     uneasy
    0.95
     compelled
    0.93
     vibrations
    0.90
     uncomfortable
    0.87
     confident
    0.85
    rils
    0.85
     discomfort
    0.81
     sorry
    0.80
     sensations
    0.78
    Activations Density 0.043%

    No Known Activations