© 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. 11-RES-JB
    11. 21246
    Prev
    Next
    INDEX
    Explanations

    words related to levels or extremes

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant highs or lows in various metrics or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dishes
    -0.64
     tattoos
    -0.60
    enegger
    -0.60
    minist
    -0.60
    sbm
    -0.60
     Memories
    -0.59
     regrets
    -0.58
    oided
    -0.57
    mails
    -0.57
     faithfully
    -0.56
    POSITIVE LOGITS
     heights
    1.15
     level
    1.13
     point
    1.03
     height
    1.03
     plateau
    1.03
     pinnacle
    0.98
     levels
    0.96
     threshold
    0.94
     saturation
    0.94
     extent
    0.93
    Activations Density 0.148%

    No Known Activations