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. 18285
    Prev
    Next
    INDEX
    Explanations

    phrases related to exerting effort or control over a particular situation or domain

    oai_token-act-pair · gpt-3.5-turbo

    references to running or managing activities and associated risks

    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
    ema
    -0.79
    ayers
    -0.78
    iatus
    -0.73
    orrow
    -0.72
    tymology
    -0.69
    gdala
    -0.66
    Artist
    -0.63
    ESA
    -0.63
     Chomsky
    -0.63
    oult
    -0.62
    POSITIVE LOGITS
     smoothly
    1.06
     simulations
    0.96
    auntlet
    0.90
     err
    0.88
     gam
    0.86
     affairs
    0.83
     efficiently
    0.83
     risk
    0.81
     marathon
    0.80
     tests
    0.79
    Activations Density 0.095%

    No Known Activations