© 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. 4-RES-JB
    11. 7390
    Prev
    Next
    INDEX
    Explanations

    specific names, particularly "Glen"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Glen"

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

    No Comments

    Negative Logits
    oÄŁ
    -0.71
    ÄŁ
    -0.70
    enance
    -0.68
     subp
    -0.67
    ãģĭ
    -0.67
    Ĥİ
    -0.66
    initialized
    -0.65
    catentry
    -0.63
    unin
    -0.62
     inherit
    -0.62
    POSITIVE LOGITS
    coe
    1.11
    gow
    0.91
    boro
    0.91
    brook
    0.89
    iths
    0.89
    wyn
    0.88
    burn
    0.88
    stones
    0.86
    forth
    0.85
    oche
    0.85
    Activations Density 0.009%

    No Known Activations