© 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. 9-RES-JB
    11. 6433
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitions or events labeled as "ultimate."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gone
    -0.81
    metic
    -0.78
    istically
    -0.78
    holes
    -0.76
    lessly
    -0.75
    ullivan
    -0.75
     wart
    -0.74
    igning
    -0.74
    usra
    -0.73
    gy
    -0.73
    POSITIVE LOGITS
     Edition
    1.33
     Collection
    1.23
     Materials
    1.16
     Partnership
    1.14
     Bundle
    1.14
     Distribution
    1.11
     Excellence
    1.08
     Collections
    1.06
     Membership
    1.06
     Solutions
    1.05
    Activations Density 0.140%

    No Known Activations