© 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. 18541
    Prev
    Next
    INDEX
    Explanations

    political debate and rhetoric terms

    oai_token-act-pair · gpt-3.5-turbo

    expressions of criticism or mockery in discourse

    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
    ESE
    -0.82
     Located
    -0.78
     Pwr
    -0.74
    Owner
    -0.74
    SEA
    -0.74
    owned
    -0.72
    eeper
    -0.71
    region
    -0.70
    Located
    -0.69
    ELS
    -0.69
    POSITIVE LOGITS
     plat
    1.49
     clich
    1.46
     excuses
    1.45
     rhetoric
    1.39
     whining
    1.37
     jargon
    1.36
     slogans
    1.35
     nonsense
    1.35
     rhetorical
    1.34
     euphem
    1.31
    Activations Density 0.586%

    No Known Activations