© 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. 16555
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms related to organizations and individuals

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to organizations or groups

    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
    izu
    -0.65
    taboola
    -0.65
    osphere
    -0.64
    bat
    -0.64
    âĶģ
    -0.64
     Cree
    -0.63
    swer
    -0.63
     Bain
    -0.63
    erva
    -0.62
    âķ
    -0.61
    POSITIVE LOGITS
     Chairman
    1.13
     officials
    1.07
     Chair
    1.04
     Commissioner
    1.02
     member
    1.02
     chairman
    1.00
     Director
    0.99
     inspectors
    0.99
     members
    0.96
     commissioner
    0.95
    Activations Density 0.147%

    No Known Activations