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. 9-RES-JB
    6. 12724
    Prev
    Next
    INDEX
    Explanations

    phrases related to production, printing, and translation

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to various contexts, especially those indicating registration, involvement, or production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wolves
    -0.67
    ses
    -0.65
    osaurs
    -0.64
    owers
    -0.62
     Flavoring
    -0.62
    dor
    -0.62
    zes
    -0.61
    acks
    -0.61
     Turks
    -0.57
    casters
    -0.57
    POSITIVE LOGITS
    inently
    0.79
     chiefly
    0.78
    ensibly
    0.78
    ãĤ´
    0.76
    ĸļ
    0.76
     primarily
    0.74
     principally
    0.73
    ivating
    0.73
    itionally
    0.70
    enced
    0.69
    Activations Density 0.367%

    No Known Activations