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. 7692
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" followed by verbs in infinitive form

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions or purposes

    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
     largeDownload
    -0.66
    listed
    -0.65
    nces
    -0.63
    soDeliveryDate
    -0.62
     Appears
    -0.60
    reports
    -0.58
    tesy
    -0.57
     Caption
    -0.57
    resy
    -0.57
    quickShipAvailable
    -0.56
    POSITIVE LOGITS
     maximize
    1.04
     achieve
    1.01
     avoid
    1.01
     compensate
    1.00
     defend
    1.00
     conserve
    1.00
     satisfy
    0.99
     minimize
    0.99
     fulfill
    0.96
     preserve
    0.96
    Activations Density 0.972%

    No Known Activations