© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 3975
    Prev
    Next
    INDEX
    Explanations

    words related to demonstrations or protests

    oai_token-act-pair · gpt-3.5-turbo

    references to "Demon" or "demons" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tta
    -0.64
    giving
    -0.64
    gow
    -0.62
    ACP
    -0.61
    ozy
    -0.61
     Obesity
    -0.60
     dearly
    -0.59
    lahoma
    -0.59
    tis
    -0.59
    oldown
    -0.59
    POSITIVE LOGITS
    stration
    1.31
    strate
    1.00
     Demon
    0.83
    demon
    0.82
    Demon
    0.81
    ected
    0.77
    inators
    0.76
    bre
    0.75
    pled
    0.75
    fuck
    0.74
    Activations Density 0.012%

    No Known Activations