© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16327
    Prev
    Next
    INDEX
    Explanations

    terms related to emotions and sentiments, specifically those associated with warmth and kindness

    oai_token-act-pair · gpt-3.5-turbo

    words associated with warmth, kindness, or positivity in human interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.86
    aeda
    -0.73
    abases
    -0.67
    raviolet
    -0.67
    assic
    -0.67
    igate
    -0.67
    URA
    -0.66
    agles
    -0.66
    yer
    -0.66
    inates
    -0.65
    POSITIVE LOGITS
    hearted
    1.35
    ness
    0.99
     tone
    0.87
    tons
    0.85
     endeavour
    0.80
     banter
    0.78
     upbeat
    0.77
    heartedly
    0.77
     endeavor
    0.75
     kindness
    0.74
    Activations Density 0.030%

    No Known Activations