© 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. 10-RES-JB
    11. 12127
    Prev
    Next
    INDEX
    Explanations

    keywords related to website analytics, such as "visits," "views," "comments," and "user interactions."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toug
    -0.78
     scapego
    -0.73
     balk
    -0.72
     caution
    -0.71
     fundamentalist
    -0.70
     reneg
    -0.70
     reluctance
    -0.69
     pacif
    -0.69
     deregulation
    -0.68
     wary
    -0.68
    POSITIVE LOGITS
    Total
    1.11
     total
    1.08
    total
    1.06
     TOTAL
    1.06
     avg
    1.04
     Total
    1.03
     Average
    1.00
     Completed
    1.00
     Avg
    0.98
    Completed
    0.96
    Activations Density 0.421%

    No Known Activations