© 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. 3456
    Prev
    Next
    INDEX
    Explanations

    keywords indicating a comparison or contrast between different situations or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "While" indicating conditional or contrasting statements

    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
    SPONSORED
    -0.83
    ISE
    -0.81
    tnc
    -0.77
    INS
    -0.74
    illet
    -0.72
    DragonMagazine
    -0.70
    ALD
    -0.69
    bas
    -0.69
    rium
    -0.69
    die
    -0.69
    POSITIVE LOGITS
     acknowledging
    1.26
     researching
    1.08
     conced
    1.02
     discussing
    0.92
     respecting
    0.92
     maintaining
    0.92
     technically
    0.91
     admitting
    0.91
     browsing
    0.91
     agreeing
    0.88
    Activations Density 0.055%

    No Known Activations