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. 1-RES-JB
    6. 8419
    Prev
    Next
    INDEX
    Explanations

    words related to strong negative emotions, specifically sadness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness

    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
    VERTISEMENT
    -0.79
    RAFT
    -0.73
    Newsletter
    -0.71
    byter
    -0.65
    IPP
    -0.63
    naires
    -0.63
    herical
    -0.63
    Testing
    -0.63
    gemony
    -0.62
    ilogy
    -0.62
    POSITIVE LOGITS
    der
    1.13
    omas
    1.06
     sad
    1.01
    istically
    0.98
    istic
    0.94
    Sad
    0.93
    stal
    0.87
    istical
    0.82
     sus
    0.75
    sty
    0.74
    Activations Density 0.004%

    No Known Activations