© 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. 2-RES-JB
    11. 388
    Prev
    Next
    INDEX
    Explanations

    the word "feelings."

    oai_token-act-pair · gpt-4-turbo

    descriptions containing emotions or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    references to emotions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.72
    ded
    -0.68
    err
    -0.63
    photos
    -0.62
    agher
    -0.60
    Dou
    -0.60
    design
    -0.59
    lder
    -0.59
    wald
    -0.59
     Twin
    -0.58
    POSITIVE LOGITS
     feelings
    1.10
    terness
    0.98
    terday
    0.87
     sensations
    0.86
     aversion
    0.85
     affection
    0.84
     sentiments
    0.84
    otions
    0.80
    uated
    0.79
     emotions
    0.78
    Activations Density 0.009%

    No Known Activations