© 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. 6888
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to genetics or being a genius

    oai_token-act-pair · gpt-3.5-turbo

    variants of the word "genocide" and related terms

    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
     Parish
    -0.77
    cffffcc
    -0.75
    letal
    -0.72
    ¿½
    -0.71
    vati
    -0.69
    graduate
    -0.69
    enez
    -0.65
    psc
    -0.65
    yrinth
    -0.65
    landish
    -0.62
    POSITIVE LOGITS
    iuses
    1.26
    ocide
    1.26
     gen
    1.12
    uin
    1.03
    omics
    1.01
    otypes
    0.95
    uine
    0.95
    otype
    0.93
    iors
    0.91
    otyp
    0.90
    Activations Density 0.003%

    No Known Activations