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. 10-RES-JB
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    the pattern "ae" in words

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "ae" and its occurrences in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICK
    -0.84
    naire
    -0.77
    naires
    -0.74
    icked
    -0.70
    agers
    -0.69
    lich
    -0.69
     Canadiens
    -0.67
    ENTION
    -0.66
    rified
    -0.66
    aged
    -0.66
    POSITIVE LOGITS
    hler
    1.11
    gypt
    1.02
    lyn
    1.01
    lect
    1.00
    bsite
    0.99
    ldon
    0.96
    hner
    0.94
    zza
    0.94
    ger
    0.93
    lder
    0.93
    Activations Density 0.025%

    No Known Activations