© 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. 10-RES-JB
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    general terms that are commonly associated with various types of groups or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to general group characteristics or commonalities

    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
    NI
    -0.71
    ornia
    -0.71
    Pad
    -0.70
    kefeller
    -0.69
    anooga
    -0.67
    ARE
    -0.67
    dor
    -0.66
    bley
    -0.66
    thouse
    -0.66
    ħĭ
    -0.65
    POSITIVE LOGITS
     others
    0.86
     other
    0.83
     else
    0.74
     nascent
    0.73
     great
    0.72
     revolutions
    0.70
     good
    0.70
     mammals
    0.68
     totalitarian
    0.67
     civilized
    0.67
    Activations Density 0.095%

    No Known Activations