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. 0-RES-JB
    6. 9252
    Prev
    Next
    INDEX
    Explanations

    words related to the word "owl"

    oai_token-act-pair · gpt-3.5-turbo

    references to "owl" or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vant
    -0.76
     dated
    -0.71
     Deb
    -0.65
     dating
    -0.64
     sourced
    -0.61
     Christian
    -0.61
     insertion
    -0.61
     Liberal
    -0.60
     Juno
    -0.60
     salv
    -0.59
    POSITIVE LOGITS
    owl
    4.83
    owler
    1.42
     owl
    1.19
    bowl
    1.11
     Owl
    1.10
    ogs
    1.08
     ow
    1.06
    ows
    1.03
    ooth
    1.00
    awks
    0.99
    Activations Density 0.012%

    No Known Activations