© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    6. 7965
    Prev
    Next
    INDEX
    Explanations

    words related to sympathy or empathy

    oai_token-act-pair · gpt-3.5-turbo

    references to sympathy and empathy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fail
    -0.71
    raft
    -0.70
     Grind
    -0.68
     DT
    -0.68
    Drag
    -0.65
     Printing
    -0.65
    Ds
    -0.64
     UT
    -0.64
    dd
    -0.64
     Ruin
    -0.64
    POSITIVE LOGITS
     sympathy
    3.01
     sympathetic
    2.84
     empathy
    2.52
     sympath
    2.29
     empath
    2.22
     compassion
    1.95
     pity
    1.80
     symp
    1.57
     compassionate
    1.47
     condolences
    1.28
    Activations Density 0.022%

    No Known Activations