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. 8-RES-JB
    6. 14751
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency

    oai_token-act-pair · gpt-3.5-turbo

    the word "every" and its variations, indicating a focus on inclusivity or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olas
    -0.77
    phabet
    -0.75
    dict
    -0.68
    isson
    -0.63
    ees
    -0.62
     Presence
    -0.61
     Graves
    -0.61
    quished
    -0.58
     Osw
    -0.58
     Prompt
    -0.57
    POSITIVE LOGITS
    THING
    1.58
     conceivable
    1.48
     imaginable
    1.38
    where
    1.11
     single
    1.08
     inch
    1.05
     ounce
    1.02
    single
    1.02
    thin
    1.01
     aspect
    1.00
    Activations Density 0.047%

    No Known Activations