© 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. 2755
    Prev
    Next
    INDEX
    Explanations

    phrases related to unexpected events or plot twists

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a change or twist in events

    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
    VICE
    -0.76
    lain
    -0.74
     uncond
    -0.69
    leground
    -0.67
    Demand
    -0.64
    mobi
    -0.64
    ials
    -0.62
    ļéĨĴ
    -0.60
     Consumers
    -0.59
     Parenthood
    -0.59
    POSITIVE LOGITS
    phrase
    0.83
     phrase
    0.83
     fortune
    0.81
     tides
    0.73
     hindsight
    0.73
     fate
    0.72
     dawn
    0.71
     fortunes
    0.70
    fortune
    0.70
     midnight
    0.68
    Activations Density 0.105%

    No Known Activations