© 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. 10-RES-JB
    11. 20321
    Prev
    Next
    INDEX
    Explanations

    words related to specific names, particularly those starting with "Ru"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ruiz" and its variations in different contexts

    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
    sie
    -0.77
    £ı
    -0.76
     fences
    -0.67
     Seym
    -0.65
     HELL
    -0.64
     Remastered
    -0.64
     Cerberus
    -0.62
    chool
    -0.61
    spread
    -0.60
    20439
    -0.60
    POSITIVE LOGITS
    pees
    1.45
    pee
    1.33
    pert
    1.21
    ination
    1.16
    ined
    1.15
    Paul
    1.08
    pport
    1.04
    inous
    1.02
    fty
    1.00
    ining
    1.00
    Activations Density 0.016%

    No Known Activations