© 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. 9-RES-JB
    11. 23527
    Prev
    Next
    INDEX
    Explanations

    new product launches or introductions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of new product launches and innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensen
    -0.67
    pson
    -0.62
    76561
    -0.60
    idences
    -0.57
     knees
    -0.55
    eties
    -0.55
     accidents
    -0.54
    istered
    -0.54
    asser
    -0.53
    enery
    -0.53
    POSITIVE LOGITS
     featuring
    0.90
     consisting
    0.84
     modeled
    0.83
     exclusively
    0.80
     dubbed
    0.80
     showcasing
    0.79
     aimed
    0.78
     incorporating
    0.77
     titled
    0.75
     highlighting
    0.74
    Activations Density 0.485%

    No Known Activations