© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22216
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Eduardo"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to the name "Ardo" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UR
    -0.69
    orial
    -0.68
    ivities
    -0.68
     HL
    -0.67
     CTRL
    -0.66
    IVES
    -0.64
    oration
    -0.61
    OWER
    -0.60
     CBI
    -0.60
    rust
    -0.60
    POSITIVE LOGITS
    zzi
    1.22
    ardo
    1.12
     Paulo
    1.05
    atta
    0.99
    ragon
    0.93
    lette
    0.87
    quez
    0.86
    vernment
    0.85
    ÄŁ
    0.85
     Duterte
    0.84
    Activations Density 0.004%

    No Known Activations