© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 24104
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions, specifically sadness and disappointment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness and sorrow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 1 - sadness

    No Comments

    Negative Logits
    aminer
    -0.68
    ameron
    -0.64
     drilled
    -0.64
    hibition
    -0.64
    eva
    -0.64
    Murray
    -0.63
    smoking
    -0.63
     fitt
    -0.62
    iciency
    -0.62
    orum
    -0.61
    POSITIVE LOGITS
     saddened
    1.00
     sadness
    0.91
     condolences
    0.91
     mourn
    0.90
    terday
    0.82
    bringer
    0.81
    isSpecialOrderable
    0.79
     sorrow
    0.79
    mares
    0.79
     remembrance
    0.78
    Activations Density 0.011%

    No Known Activations