Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14645
    Prev
    Next
    INDEX
    Explanations

    words related to sympathy or empathy

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sympathy and empathy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stall
    -0.90
    eor
    -0.83
    corn
    -0.80
    nos
    -0.73
    growth
    -0.72
    ouver
    -0.71
    teen
    -0.66
    aer
    -0.66
    ravis
    -0.66
    nen
    -0.66
    POSITIVE LOGITS
     sympath
    0.97
    arity
    0.92
     sympathy
    0.82
     solidarity
    0.77
    axter
    0.74
     empath
    0.72
     Cosponsors
    0.72
     towards
    0.72
     feelings
    0.69
     gesture
    0.68
    Activations Density 0.054%

    No Known Activations