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. 4-RES-JB
    6. 5494
    Prev
    Next
    INDEX
    Explanations

    mentions of ink-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "inks" and its variations

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

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.82
     earthqu
    -0.66
    enough
    -0.65
    translation
    -0.64
     Sharif
    -0.64
    IFA
    -0.64
     contend
    -0.63
    ãĥ¤
    -0.62
     conv
    -0.60
     compr
    -0.60
    POSITIVE LOGITS
    hips
    0.91
    edin
    0.87
    manship
    0.86
    omething
    0.86
    ipedia
    0.81
    hole
    0.80
    ionage
    0.80
    redients
    0.79
     wink
    0.79
    inks
    0.77
    Activations Density 0.011%

    No Known Activations