© 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. 6-RES-JB
    11. 17591
    Prev
    Next
    INDEX
    Explanations

    proper names related to politics or sports, specifically identifying individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in the context of events or circumstances related to death or investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneously
    -0.75
    ishable
    -0.74
    ished
    -0.73
    ATURES
    -0.73
    ners
    -0.73
    ************
    -0.72
    atted
    -0.71
    ATURE
    -0.71
    ICAN
    -0.69
    abwe
    -0.68
    POSITIVE LOGITS
     traged
    0.93
    ortment
    0.82
    ilon
    0.74
    byss
    0.73
    xus
    0.73
     unden
    0.70
    metry
    0.70
    mos
    0.68
    sembly
    0.68
    thur
    0.68
    Activations Density 0.060%

    No Known Activations