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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8384
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing something important

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating superiority or prominence

    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
    cci
    -0.73
    chie
    -0.69
    catentry
    -0.62
    anty
    -0.60
    jab
    -0.59
    arij
    -0.59
     foreseeable
    -0.58
    irez
    -0.57
    ogue
    -0.54
    ANS
    -0.54
    POSITIVE LOGITS
    boards
    0.82
    deck
    0.80
    oft
    0.80
    most
    0.78
    ography
    0.77
    mast
    0.76
    model
    0.73
     billing
    0.69
    retty
    0.68
    ographical
    0.67
    Activations Density 0.023%

    No Known Activations