© 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. 18582
    Prev
    Next
    INDEX
    Explanations

    references to people or profiles on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media activities and accounts

    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
     boarding
    -0.62
     blush
    -0.61
     mort
    -0.60
     ply
    -0.59
     dispers
    -0.59
    erous
    -0.59
     slic
    -0.57
    aging
    -0.57
     apart
    -0.57
     outl
    -0.56
    POSITIVE LOGITS
    <|endoftext|>
    0.98
     Follow
    0.96
     Alternatively
    0.91
     Fans
    0.86
     Also
    0.79
     Got
    0.79
     Find
    0.78
     Tickets
    0.77
     HELP
    0.76
     Support
    0.76
    Activations Density 0.065%

    No Known Activations