© 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. 0-RES-JB
    11. 13586
    Prev
    Next
    INDEX
    Explanations

    references to General Packet Radio Service (GPRS) settings or similar technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of graphics processing units (GPUs) and related technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turkey
    -0.68
     Lauder
    -0.63
     sund
    -0.61
     nesting
    -0.61
     Crowley
    -0.60
     Lindsey
    -0.60
     waters
    -0.60
     tribes
    -0.59
     Clay
    -0.58
     singers
    -0.58
    POSITIVE LOGITS
    GP
    4.59
    gp
    2.07
     GP
    1.91
    Gi
    1.42
    GT
    1.38
    GS
    1.32
    ACP
    1.30
    PG
    1.29
    GM
    1.28
     GPIO
    1.25
    Activations Density 0.017%

    No Known Activations