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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11181
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "nylon"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and materials associated with items or people

    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
    Fed
    -0.84
     Sponsor
    -0.80
     DHCP
    -0.74
     McCain
    -0.73
    Host
    -0.71
     Host
    -0.71
    UFC
    -0.68
     Kemp
    -0.67
     Cheong
    -0.67
     Ski
    -0.66
    POSITIVE LOGITS
    ylon
    2.23
    olis
    2.18
    cyl
    1.59
     cylinders
    1.55
    yl
    1.52
     cylinder
    1.50
    ylene
    1.28
     Miranda
    1.27
     Lor
    1.27
     Vinyl
    1.14
    Activations Density 0.050%

    No Known Activations