© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17735
    Prev
    Next
    INDEX
    Explanations

    positive and negative adjectives related to feelings

    oai_token-act-pair · gpt-3.5-turbo

    words associated with positive and negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.79
    bard
    -0.72
    uilding
    -0.71
    chart
    -0.69
    asio
    -0.68
    athlon
    -0.68
    fund
    -0.66
    cells
    -0.65
    elson
    -0.65
    arnaev
    -0.64
    POSITIVE LOGITS
     surprises
    1.18
     nuisance
    0.99
    lihood
    0.92
    ries
    0.85
     surprise
    0.85
     smelling
    0.84
     smells
    0.80
     pests
    0.80
    liness
    0.79
     odor
    0.78
    Activations Density 0.131%

    No Known Activations