Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 20904
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression over time or achievement

    oai_token-act-pair · gpt-3.5-turbo

    references to developmental progress and changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     investigates
    -0.68
     lately
    -0.67
     tries
    -0.66
    try
    -0.66
     Sometimes
    -0.65
     strives
    -0.65
    bol
    -0.64
     defends
    -0.64
     purposes
    -0.64
     upbringing
    -0.63
    POSITIVE LOGITS
     exhausted
    0.87
     already
    0.85
    Already
    0.77
    ©¶æ¥µ
    0.71
    ties
    0.70
     outweigh
    0.70
     surpassed
    0.69
    enough
    0.69
     outnumbered
    0.68
     Already
    0.68
    Activations Density 0.250%

    No Known Activations