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. 6-RES-JB
    6. 23654
    Prev
    Next
    INDEX
    Explanations

    phrases related to data sharing or distribution percentages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial metrics and distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jad
    -0.86
    wcs
    -0.76
    actionDate
    -0.71
    dayName
    -0.71
    miah
    -0.70
    \\\\\\\\
    -0.68
     recip
    -0.67
    ãĤ¡
    -0.66
    ients
    -0.65
    æĦ
    -0.64
    POSITIVE LOGITS
     GDP
    0.86
     variance
    0.76
     total
    0.62
     GN
    0.61
     each
    0.61
     Dollars
    0.60
     proportional
    0.59
     eligible
    0.58
    arching
    0.58
     blame
    0.58
    Activations Density 0.075%

    No Known Activations