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. 3-RES-JB
    6. 19493
    Prev
    Next
    INDEX
    Explanations

    text related to legal or financial obligations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duties and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vill
    -0.69
    vae
    -0.69
    stocks
    -0.68
     Tate
    -0.66
    ican
    -0.66
     Onion
    -0.65
    atin
    -0.65
     Tid
    -0.64
     Spray
    -0.64
    auder
    -0.63
    POSITIVE LOGITS
     obligations
    1.14
     obligation
    1.11
     obliged
    1.09
     owed
    0.99
     obligated
    0.99
     incurred
    0.94
     allegiance
    0.78
     challeng
    0.76
     entrusted
    0.75
     Compliance
    0.75
    Activations Density 0.014%

    No Known Activations