© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 3558
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically "Welch" and "Leah"

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to notable people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cyrus
    -0.79
     Julio
    -0.73
     Pebble
    -0.73
     Bib
    -0.72
     æľ
    -0.71
     Rodrig
    -0.71
     Vive
    -0.70
     Tac
    -0.70
     Cele
    -0.69
     Bulg
    -0.68
    POSITIVE LOGITS
    wagen
    0.93
    ambers
    0.93
    veyard
    0.91
    iless
    0.83
    ifted
    0.82
    anged
    0.82
    arnaev
    0.81
    umbers
    0.81
    aughtered
    0.81
    chnology
    0.80
    Activations Density 0.034%

    No Known Activations