© 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. 10-RES-JB
    11. 2325
    Prev
    Next
    INDEX
    Explanations

    words related to significant importance or impact

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate importance or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    events
    -1.01
    hops
    -0.97
    iddles
    -0.87
    units
    -0.86
    stories
    -0.83
     Units
    -0.82
    stocks
    -0.82
    hots
    -0.82
    classes
    -0.82
    letters
    -0.81
    POSITIVE LOGITS
     amount
    1.03
     rift
    1.02
     foothold
    0.98
     uptick
    0.97
     dose
    0.95
     chunk
    0.94
     burden
    0.94
     challenge
    0.92
     resemblance
    0.91
     advantage
    0.91
    Activations Density 0.214%

    No Known Activations