© 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. 7-RES-JB
    11. 17268
    Prev
    Next
    INDEX
    Explanations

    associations regarding controversy, criticism, and pressure related to various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political pressure and scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    ".[
    -0.67
     [&
    -0.64
    âĢ¦]
    -0.63
    .[
    -0.63
     haha
    -0.63
    66666666
    -0.63
    ?".
    -0.62
    ··
    -0.62
    Anyway
    -0.62
    POSITIVE LOGITS
     controversies
    1.01
     controversy
    0.97
     contentious
    0.94
     feud
    0.91
     outspoken
    0.90
     dogged
    0.89
     controversial
    0.85
     accuse
    0.81
     criticism
    0.79
     controvers
    0.79
    Activations Density 0.782%

    No Known Activations