© 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. 11-RES-JB
    11. 17332
    Prev
    Next
    INDEX
    Explanations

    text related to specific parts of the brain, particularly the motor cortex and prefrontal cortex

    oai_token-act-pair · gpt-3.5-turbo

    terms related to brain regions and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Weather
    -0.65
     Hour
    -0.64
    emort
    -0.64
    Disclaimer
    -0.64
     Tomorrow
    -0.63
    chn
    -0.60
    =-=-
    -0.60
    Applic
    -0.60
    morrow
    -0.59
    Mist
    -0.59
    POSITIVE LOGITS
     neurons
    1.18
     implicated
    1.11
     regulates
    0.99
     regulating
    0.99
     responsible
    0.98
    responsible
    0.97
     involved
    0.96
     located
    0.94
     neurotrans
    0.93
     serotonin
    0.93
    Activations Density 0.186%

    No Known Activations