© 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. 20352
    Prev
    Next
    INDEX
    Explanations

    words related to emotional reactions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "Ļ" in the text

    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
     Skydragon
    -0.72
     streng
    -0.64
     Opportun
    -0.64
     opportunities
    -0.63
     unaff
    -0.62
     catast
    -0.62
     eyeb
    -0.62
     decomp
    -0.62
     Jem
    -0.61
     fragmentation
    -0.61
    POSITIVE LOGITS
    rm
    0.88
    α
    0.77
    Ļ
    0.76
    ¢
    0.74
    lvl
    0.74
    rd
    0.73
    ril
    0.73
    din
    0.72
    ll
    0.72
    lation
    0.70
    Activations Density 0.206%

    No Known Activations