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. 19655
    Prev
    Next
    INDEX
    Explanations

    verbs associated with fulfilling obligations or completing tasks

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "fulfill."

    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
    uyomi
    -0.76
    Downloadha
    -0.72
    otin
    -0.67
    brow
    -0.65
    oxin
    -0.62
    affer
    -0.60
    ARC
    -0.59
     venom
    -0.58
    oss
    -0.58
     inh
    -0.57
    POSITIVE LOGITS
     fulf
    1.14
     fulfil
    1.13
     fulfilled
    1.05
     fulfillment
    1.04
     fulfill
    0.92
    ances
    0.87
    ments
    0.85
    ment
    0.84
    ance
    0.84
    soDeliveryDate
    0.81
    Activations Density 0.013%

    No Known Activations