Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 837
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Dur"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Dur

    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
     IPO
    -0.84
    BUS
    -0.78
     overt
    -0.72
    cheat
    -0.70
     forgiven
    -0.68
     internship
    -0.67
    cross
    -0.66
     breast
    -0.63
     belly
    -0.62
    forward
    -0.62
    POSITIVE LOGITS
     Dur
    3.91
    Dur
    3.09
     dur
    1.94
     durability
    1.30
     Dek
    1.16
     Zur
    1.16
     Dun
    1.13
     Durham
    1.11
     Dum
    1.04
    Dun
    1.04
    Activations Density 0.027%

    No Known Activations