© 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. 10-RES-JB
    11. 16547
    Prev
    Next
    INDEX
    Explanations

    phrases related to political rhetoric and discourse

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that might represent special formatting or non-standard text elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shroud
    -0.81
     dispers
    -0.78
     sled
    -0.76
     assemb
    -0.76
     recogn
    -0.72
     nude
    -0.71
    conservancy
    -0.71
     closest
    -0.70
     shack
    -0.69
     distribut
    -0.68
    POSITIVE LOGITS
    ¬
    1.60
    ľ
    1.59
    ¡
    1.59
    «
    1.48
    ª
    1.47
    Ļ
    1.44
    ł
    1.42
    ĸ
    1.41
    Ł
    1.41
    µ
    1.39
    Activations Density 0.144%

    No Known Activations