© 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. 115
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames starting with '@' and words occurring before them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media handles or usernames

    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
     cooperative
    -0.79
     favor
    -0.77
     compress
    -0.75
     boiler
    -0.74
     Takeru
    -0.74
     focusing
    -0.74
     referendum
    -0.73
     SEAL
    -0.73
     traditionally
    -0.72
     ranging
    -0.72
    POSITIVE LOGITS
    thereal
    1.49
    Real
    1.43
    dan
    1.33
    Coach
    1.33
    Official
    1.33
    jac
    1.32
    mr
    1.29
    mc
    1.28
    BBC
    1.28
    greg
    1.27
    Activations Density 0.034%

    No Known Activations