© 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. 8115
    Prev
    Next
    INDEX
    Explanations

    phrases related to a wide range or variety of topics or items

    oai_token-act-pair · gpt-3.5-turbo

    broad and diverse categories or groups

    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
     largeDownload
    -0.90
     mockery
    -0.74
    ĸļ
    -0.72
     lest
    -0.69
     scorn
    -0.67
    Tro
    -0.67
     bulldo
    -0.66
     exaggeration
    -0.63
    Dialogue
    -0.63
    cknowled
    -0.62
    POSITIVE LOGITS
     clients
    1.11
     sectors
    1.06
     customers
    1.01
     purposes
    0.99
     categories
    0.97
     users
    0.96
     industries
    0.95
     subjects
    0.94
     scenarios
    0.92
     countries
    0.92
    Activations Density 0.444%

    No Known Activations