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. 10-RES-JB
    6. 21171
    Prev
    Next
    INDEX
    Explanations

    questions about timing and scheduling

    oai_token-act-pair · gpt-3.5-turbo

    questions about timelines and scheduling events

    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
    eret
    -0.72
    Ĥª
    -0.71
    ¿½
    -0.66
     Tos
    -0.62
     notwithstanding
    -0.56
     aiding
    -0.56
    bnb
    -0.55
    00007
    -0.54
     Vector
    -0.53
    rn
    -0.53
    POSITIVE LOGITS
     finally
    1.04
     expire
    1.02
     commence
    0.94
     begin
    0.90
     arrive
    0.85
     officially
    0.85
     expires
    0.84
     start
    0.83
     reopen
    0.83
     finished
    0.82
    Activations Density 0.182%

    No Known Activations