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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13824
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to crying or emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tears" and related emotional expressions

    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
    iat
    -0.70
    abase
    -0.67
    irm
    -0.66
     advisory
    -0.66
     Distribution
    -0.63
    ahan
    -0.61
    ichi
    -0.60
    itzer
    -0.60
     Citation
    -0.60
     Nir
    -0.59
    POSITIVE LOGITS
     tears
    4.46
     Tears
    2.49
     tear
    1.99
     weeping
    1.63
     weep
    1.41
     bruises
    1.29
     crying
    1.28
     smiles
    1.28
     stitches
    1.25
     tearing
    1.24
    Activations Density 0.017%

    No Known Activations