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. 11-RES-JB
    6. 2934
    Prev
    Next
    INDEX
    Explanations

    words related to responsibility and obligation

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate obligation or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Birth
    -0.80
     Bust
    -0.70
     rave
    -0.69
     Volcano
    -0.66
     greatness
    -0.66
     Lift
    -0.65
     staple
    -0.63
     rebirth
    -0.63
     Graveyard
    -0.63
     crossover
    -0.63
    POSITIVE LOGITS
     willing
    1.43
     inclined
    1.35
     unwilling
    1.34
     aware
    1.34
     obliged
    1.31
     confident
    1.26
     reluctant
    1.25
     persuaded
    1.25
     obligated
    1.24
     satisfied
    1.15
    Activations Density 0.305%

    No Known Activations