© 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. 17424
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy and strong negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to public outrage and controversy

    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
    nosis
    -0.67
    ©¶æ
    -0.64
    0000000000000000
    -0.63
     Substance
    -0.57
     bye
    -0.56
    uration
    -0.54
     commandments
    -0.54
    >[
    -0.54
     ESV
    -0.53
    Entry
    -0.53
    POSITIVE LOGITS
     among
    1.32
     amongst
    1.20
     across
    1.06
     internationally
    1.03
     worldwide
    1.01
    among
    0.99
     nationwide
    0.99
     nationally
    0.96
     domestically
    0.94
     abroad
    0.94
    Activations Density 0.164%

    No Known Activations