© 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. 15614
    Prev
    Next
    INDEX
    Explanations

    verbs related to changes or actions that have a significant impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant life events or changes

    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
    wcsstore
    -0.86
    pmwiki
    -0.70
    PI
    -0.66
    =-=-
    -0.66
     COURT
    -0.64
     Proceed
    -0.63
     TOD
    -0.63
     Regarding
    -0.63
    sim
    -0.62
    Ingredients
    -0.61
    POSITIVE LOGITS
     millions
    1.09
     countless
    1.03
     untold
    0.98
     humankind
    0.94
     mankind
    0.90
     thousands
    0.89
     revolution
    0.87
     innumerable
    0.86
     revolutions
    0.86
     billions
    0.85
    Activations Density 0.401%

    No Known Activations