© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6445
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing that a particular subject is not limited to one specific thing or category

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsequ
    -0.79
     concess
    -0.78
    stress
    -0.67
    ItemTracker
    -0.66
    adish
    -0.65
     seiz
    -0.65
     ABV
    -0.63
     Remastered
    -0.62
     respectively
    -0.62
    oided
    -0.62
    POSITIVE LOGITS
    ifiable
    1.22
    ifications
    0.85
    IFIED
    0.73
    itia
    0.72
     coincidence
    0.70
    ivity
    0.66
     anymore
    0.66
    XM
    0.65
    ones
    0.64
     deserts
    0.63
    Activations Density 0.056%

    No Known Activations