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. 1-RES-JB
    6. 8444
    Prev
    Next
    INDEX
    Explanations

    verbs related to completing a task or obligation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fulfill" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.84
    otin
    -0.76
    Downloadha
    -0.70
    apple
    -0.66
     Hayden
    -0.63
    appropri
    -0.62
    ker
    -0.62
    affer
    -0.61
     spray
    -0.61
    ayan
    -0.59
    POSITIVE LOGITS
     fulfilled
    1.32
     fulf
    1.23
     fulfil
    1.22
     fulfillment
    1.19
     fulfill
    1.14
     fulfilling
    1.01
    soDeliveryDate
    0.92
     âĶľ
    0.84
     SERV
    0.83
    ãĤ¤ãĥĪ
    0.78
    Activations Density 0.008%

    No Known Activations