© 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. 0-RES-JB
    11. 22618
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "widow"

    oai_token-act-pair · gpt-3.5-turbo

    references to widows or widowhood

    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
    emy
    -0.69
     align
    -0.65
     unic
    -0.61
     motiv
    -0.60
     MEN
    -0.60
     Mash
    -0.59
    addin
    -0.59
    fits
    -0.59
    Fed
    -0.56
     shifts
    -0.56
    POSITIVE LOGITS
     widow
    3.29
     Widow
    1.33
     descendant
    0.92
     descendants
    0.84
     grieving
    0.77
    Lee
    0.77
     granddaughter
    0.77
     Decay
    0.76
     MU
    0.72
     polymer
    0.72
    Activations Density 0.011%

    No Known Activations