© 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. 9-RES-JB
    11. 6990
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or activity

    oai_token-act-pair · gpt-3.5-turbo

    reported actions and statements by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.96
     selves
    -0.81
    respect
    -0.78
    Daddy
    -0.74
    folk
    -0.71
     nig
    -0.71
    joice
    -0.70
    fuck
    -0.67
    VERTISEMENT
    -0.66
     naughty
    -0.65
    POSITIVE LOGITS
     himself
    1.00
     firsthand
    0.85
     PowerPoint
    0.82
     keynote
    0.79
     consultations
    0.79
     herself
    0.79
     anecd
    0.79
     anecdotal
    0.78
     colleague
    0.77
     overseeing
    0.77
    Activations Density 0.733%

    No Known Activations