© 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. 4-RES-JB
    11. 6866
    Prev
    Next
    INDEX
    Explanations

    emotional words associated with feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions and feelings

    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
    annis
    -0.85
    culosis
    -0.69
     Accounting
    -0.67
    zan
    -0.66
    wald
    -0.63
    err
    -0.62
    iary
    -0.62
     Amend
    -0.61
    lder
    -0.60
    amn
    -0.60
    POSITIVE LOGITS
     feelings
    1.04
    terness
    0.94
     sensations
    0.86
    æĦ
    0.82
     aversion
    0.80
    pring
    0.77
     affection
    0.76
     sentiments
    0.76
    ual
    0.75
     emotions
    0.75
    Activations Density 0.020%

    No Known Activations