© 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. 0-RES-JB
    11. 5367
    Prev
    Next
    INDEX
    Explanations

    names or specific terms related to the concept of "Cyprus"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Cy" and related elements within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vernon
    -0.76
     Alma
    -0.70
     Abraham
    -0.69
     Stern
    -0.69
     flock
    -0.68
     nib
    -0.67
     grains
    -0.65
     fuss
    -0.65
     perk
    -0.65
     plaque
    -0.64
    POSITIVE LOGITS
    Cy
    3.99
    cycles
    1.39
    cycle
    1.37
    cy
    1.35
     Cycl
    1.33
    Ly
    1.28
    Ul
    1.25
     cy
    1.24
    Rh
    1.24
    Motor
    1.23
    Activations Density 0.023%

    No Known Activations