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. 9-RES-JB
    6. 18782
    Prev
    Next
    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" and its context in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mare
    -0.74
    chenko
    -0.67
    zona
    -0.66
    marine
    -0.60
    qqa
    -0.58
     nicknamed
    -0.57
    hao
    -0.56
    Learn
    -0.56
    Strike
    -0.55
    soDeliveryDate
    -0.55
    POSITIVE LOGITS
    gotten
    1.26
     reasons
    1.21
    bidden
    1.19
     purposes
    1.17
    given
    1.14
    gettable
    1.04
    ked
    1.04
    ced
    1.04
    give
    1.02
    geries
    0.99
    Activations Density 0.110%

    No Known Activations