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. 19288
    Prev
    Next
    INDEX
    Explanations

    dates expressed as a year

    oai_token-act-pair · gpt-3.5-turbo

    specific years mentioned in relation to events

    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
    elong
    -0.67
    worldly
    -0.65
    ãģį
    -0.64
    agy
    -0.64
    amins
    -0.62
     genus
    -0.61
    ousel
    -0.60
    ardless
    -0.60
     unpredictable
    -0.59
     toast
    -0.59
    POSITIVE LOGITS
     onwards
    0.89
     partName
    0.77
     sidx
    0.72
    20439
    0.70
     onward
    0.67
     Kass
    0.65
    DragonMagazine
    0.62
    â̲
    0.61
     when
    0.61
     Raphael
    0.60
    Activations Density 0.078%

    No Known Activations