© 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. 20566
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific professions or areas of expertise, like "Buddhist monk," "processed meats," and "Agricultural Center for Excellence."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places and organizations

    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
    IDER
    -0.79
     Sins
    -0.75
     Izan
    -0.75
    ider
    -0.73
     Invisible
    -0.71
     Sever
    -0.70
    332
    -0.69
     Stranger
    -0.69
     332
    -0.68
    ido
    -0.68
    POSITIVE LOGITS
    ham
    0.92
    arat
    0.79
    acs
    0.78
    705
    0.77
    70
    0.76
    hops
    0.73
    anamo
    0.73
    aches
    0.70
    pal
    0.70
    709
    0.68
    Activations Density 0.212%

    No Known Activations