© 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. 9-RES-JB
    11. 9964
    Prev
    Next
    INDEX
    Explanations

    quoted statements within text

    oai_token-act-pair · gpt-3.5-turbo

    direct quotations from individuals or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meddling
    -0.85
     riches
    -0.84
     egalitarian
    -0.84
     envy
    -0.83
     favor
    -0.83
     feminism
    -0.79
     socialist
    -0.79
     favour
    -0.79
     obsess
    -0.79
     feminists
    -0.78
    POSITIVE LOGITS
    Obviously
    1.48
    We
    1.43
    Typically
    1.41
    Certainly
    1.39
    Clearly
    1.36
    They
    1.35
    Our
    1.33
    Generally
    1.30
    Usually
    1.30
    There
    1.30
    Activations Density 0.156%

    No Known Activations