© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 2631
    Prev
    Next
    INDEX
    Explanations

    references to the name "Dylan" with varying degrees of relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Dylan"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spr
    -0.87
    rontal
    -0.82
     cryst
    -0.69
    enegger
    -0.69
     actionGroup
    -0.68
     Canary
    -0.68
    hips
    -0.68
    dayName
    -0.67
     streng
    -0.66
     satell
    -0.65
    POSITIVE LOGITS
     Dylan
    0.80
    ylan
    0.79
    owe
    0.77
    rez
    0.75
     Ezra
    0.74
     Archdemon
    0.74
     Moran
    0.74
    rine
    0.74
     Matthews
    0.73
    onymous
    0.72
    Activations Density 0.031%

    No Known Activations