© 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 EvalsExportsinterp-engineNEWAPI 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. 20956
    Prev
    Next
    INDEX
    Explanations

    references to characters and actions in a fictional narrative

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to competitions or tournaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ï¸ı
    -0.80
    STEM
    -0.77
    Wow
    -0.74
    RT
    -0.70
    Mod
    -0.68
    Kids
    -0.67
    Comments
    -0.67
    Fla
    -0.67
    iameter
    -0.66
    ä¸Ĭ
    -0.65
    POSITIVE LOGITS
     kidnapped
    1.32
     kidnap
    1.27
     betray
    1.26
     betrayed
    1.26
     assass
    1.24
     treacher
    1.22
     assassinate
    1.22
     kidn
    1.17
     kidnapping
    1.17
     assassinated
    1.15
    Activations Density 0.380%

    No Known Activations