© 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. 11-RES-JB
    11. 1494
    Prev
    Next
    INDEX
    Explanations

    proper names related to politics, sports, and literary works

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and references in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tale
    -0.72
    AMI
    -0.71
    alling
    -0.70
    isconsin
    -0.70
    elsen
    -0.69
    ksh
    -0.68
    elf
    -0.66
    ki
    -0.66
    ALS
    -0.66
    agara
    -0.65
    POSITIVE LOGITS
    mint
    0.84
    pool
    0.79
     Kers
    0.78
    mont
    0.75
    inches
    0.74
    oner
    0.73
    xus
    0.72
     Blossom
    0.72
    oqu
    0.71
     Watts
    0.70
    Activations Density 0.084%

    No Known Activations