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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7123
    Prev
    Next
    INDEX
    Explanations

    action-related phrases with a sense of urgency or intensity

    oai_token-act-pair · gpt-3.5-turbo
    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
     Tunis
    -0.70
     distribut
    -0.68
     ANC
    -0.66
     NEC
    -0.65
     Samar
    -0.65
     Nets
    -0.64
     Mali
    -0.63
     Airways
    -0.63
     Virgin
    -0.62
     planners
    -0.61
    POSITIVE LOGITS
    ½
    1.31
    Ń
    1.25
    »
    1.24
    ¹
    1.23
    £
    1.21
    º
    1.20
    ª
    1.18
    ¼
    1.10
    ¡
    1.10
    ¦
    1.09
    Activations Density 0.379%

    No Known Activations