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. 4-RES-JB
    6. 8659
    Prev
    Next
    INDEX
    Explanations

    phrases related to finishing a race or project

    oai_token-act-pair · gpt-3.5-turbo

    references to finish lines in races or competitions

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

    No Comments

    Negative Logits
    elled
    -0.75
    ulus
    -0.71
    esis
    -0.68
    orum
    -0.68
    py
    -0.66
    riad
    -0.65
    gravity
    -0.62
    resy
    -0.62
    uli
    -0.62
    ourage
    -0.61
    POSITIVE LOGITS
     finish
    0.85
     Finish
    0.82
     finishing
    0.76
     unfinished
    0.75
     bidder
    0.69
     polish
    0.68
     touches
    0.68
    nces
    0.66
    anches
    0.65
    nings
    0.64
    Activations Density 0.013%

    No Known Activations