© 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. 16712
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal life events and relationships

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of significant historical events or actions that involve leadership and relationships

    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
     WATCH
    -0.86
     GoPro
    -0.83
     pickup
    -0.82
     moms
    -0.78
     Crunch
    -0.74
    CLOSE
    -0.74
    hash
    -0.73
    Apps
    -0.73
     SUV
    -0.73
     wanna
    -0.73
    POSITIVE LOGITS
     Ferdinand
    1.01
     Trotsky
    0.95
     Augustus
    0.94
     owing
    0.94
     hostilities
    0.92
     Hitler
    0.92
     Herod
    0.91
     Engels
    0.90
     persecution
    0.90
     treacher
    0.89
    Activations Density 0.639%

    No Known Activations