© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    names which could be first and last names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically names likely related to prominent people

    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
    theless
    -0.81
    RIC
    -0.59
    ãĤº
    -0.58
    Versions
    -0.58
     Gems
    -0.56
     Pixie
    -0.56
    mining
    -0.55
    âĶĢâĶĢ
    -0.55
    âķIJ
    -0.54
    姫
    -0.54
    POSITIVE LOGITS
    ensen
    0.66
    ohan
    0.63
    atoon
    0.62
     Gaal
    0.61
    EStream
    0.59
    Keefe
    0.57
    anyon
    0.57
    ¥µ
    0.56
    zyme
    0.55
    phabet
    0.55
    Activations Density 0.122%

    No Known Activations