© 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. 5877
    Prev
    Next
    INDEX
    Explanations

    descriptions of places and activities in a travel context

    oai_token-act-pair · gpt-3.5-turbo

    sequences of actions and events occurring in a narrative

    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
    Downloadha
    -0.86
    cancer
    -0.79
    SOURCE
    -0.77
    DonaldTrump
    -0.75
    Leaks
    -0.74
    Prosecutors
    -0.74
     Nobel
    -0.73
    violence
    -0.67
     suing
    -0.67
    aghd
    -0.67
    POSITIVE LOGITS
     disembark
    1.14
     parked
    1.13
     Parking
    1.00
     parking
    0.95
     refuel
    0.94
     boarded
    0.93
     lunch
    0.93
     brisk
    0.93
    rived
    0.92
     cruising
    0.92
    Activations Density 0.460%

    No Known Activations