© 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. 17523
    Prev
    Next
    INDEX
    Explanations

    people's names being mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    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
    ramid
    -0.77
    Explore
    -0.77
    pmwiki
    -0.74
    export
    -0.72
    ilogy
    -0.70
    issions
    -0.70
    à¼
    -0.69
    Supplement
    -0.69
    esm
    -0.68
    LC
    -0.68
    POSITIVE LOGITS
     Giovanni
    1.00
     Mohamed
    0.95
     unaware
    0.91
     Abdul
    0.90
     Phillip
    0.90
     Harold
    0.90
     Gabriel
    0.89
     Caucasian
    0.88
     Vincent
    0.88
     inexperienced
    0.88
    Activations Density 0.260%

    No Known Activations