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. 12736
    Prev
    Next
    INDEX
    Explanations

    words related to being together or among a group, such as 'are' and 'among'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "are" in various contexts

    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
    dom
    -0.76
    icism
    -0.75
    uncture
    -0.64
     agre
    -0.64
    smanship
    -0.63
     Hust
    -0.62
    icter
    -0.61
    manship
    -0.61
    eus
    -0.60
    —-
    -0.59
    POSITIVE LOGITS
    wolves
    1.03
    senal
    0.96
    wolf
    0.88
    types
    0.76
     SHARES
    0.75
    Ĥª
    0.74
     embodiments
    0.73
     integers
    0.68
     photos
    0.65
    keys
    0.65
    Activations Density 0.059%

    No Known Activations