© 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. 10-RES-JB
    11. 6396
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names belonging to an asian culture

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of specific names or terms related to individuals or entities

    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
    OLOGY
    -0.61
     coli
    -0.61
    OPLE
    -0.58
     Galile
    -0.57
     PARK
    -0.57
    verages
    -0.57
     craw
    -0.56
    ONY
    -0.56
    ISON
    -0.55
    LINE
    -0.55
    POSITIVE LOGITS
    pring
    1.22
    ullivan
    1.16
    heet
    1.15
    ilon
    1.12
    chwitz
    1.10
    ugi
    1.08
    hift
    1.08
    ultan
    1.07
    wana
    1.07
    ilver
    1.07
    Activations Density 0.073%

    No Known Activations