© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8022
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or actions

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency phrases that emphasize the word "the."

    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
     because
    -0.74
    EVA
    -0.73
    VERTISEMENT
    -0.72
    itia
    -0.72
    cription
    -0.70
    Supported
    -0.69
    ãĥĺ
    -0.69
    >:
    -0.68
    provided
    -0.66
    wd
    -0.66
    POSITIVE LOGITS
     impression
    1.02
     nation
    1.00
     wearer
    0.95
     fledgling
    0.92
     ire
    0.90
     country
    0.89
     complexion
    0.87
     entire
    0.87
     nascent
    0.85
     spotlight
    0.82
    Activations Density 0.233%

    No Known Activations