© 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. 22422
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions, particularly actions involving kicking or firing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the indefinite article "a"

    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
     indications
    -0.70
     accounts
    -0.70
     interviews
    -0.70
     descriptions
    -0.69
    extreme
    -0.67
     guides
    -0.67
     actions
    -0.67
    views
    -0.66
     estimates
    -0.65
     altogether
    -0.65
    POSITIVE LOGITS
     bunch
    1.06
     few
    1.00
     chunk
    0.97
     couple
    0.97
     handful
    0.92
     boulder
    0.87
     lot
    0.87
     bit
    0.86
     swath
    0.85
     hole
    0.85
    Activations Density 0.143%

    No Known Activations