© 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. 4-RES-JB
    11. 7117
    Prev
    Next
    INDEX
    Explanations

    terms related to news articles or headlines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crime and legal issues

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

    No Comments

    Negative Logits
    vantage
    -0.71
    racuse
    -0.69
    etsk
    -0.69
    taboola
    -0.67
    baugh
    -0.67
    onomous
    -0.66
    aday
    -0.65
    agate
    -0.63
    tarian
    -0.62
    retty
    -0.62
    POSITIVE LOGITS
     EDITION
    0.98
     PRES
    0.97
    OUN
    0.97
     INV
    0.96
    INGS
    0.95
    IVES
    0.94
     SERVICE
    0.94
    ILL
    0.93
     SER
    0.92
    URES
    0.92
    Activations Density 0.176%

    No Known Activations