© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7498
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person or location

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people, primarily focusing on the name "Quinton" and variations thereof

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

    No Comments

    Negative Logits
    GER
    -0.67
     thirsty
    -0.65
    compan
    -0.62
     brow
    -0.62
    atch
    -0.61
    amaz
    -0.61
    OY
    -0.57
     benefic
    -0.57
    gypt
    -0.57
    headed
    -0.56
    POSITIVE LOGITS
    inton
    1.07
    email
    0.99
    ners
    0.86
    nel
    0.79
     Cros
    0.79
    eers
    0.77
    ium
    0.77
    ventions
    0.76
    eering
    0.76
    ieri
    0.74
    Activations Density 0.011%

    No Known Activations