© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14052
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high level or extreme point of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a critical or extreme condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Frames
    -0.69
    tty
    -0.61
    dinand
    -0.59
     Together
    -0.59
     Others
    -0.58
     Commands
    -0.58
     Fathers
    -0.57
    avorite
    -0.55
     Variant
    -0.55
     Flavoring
    -0.54
    POSITIVE LOGITS
     where
    1.00
     brink
    0.80
     whereby
    0.78
    manship
    0.75
     verge
    0.73
     whence
    0.72
    ebin
    0.72
    ophys
    0.71
    oples
    0.69
     that
    0.67
    Activations Density 0.058%

    No Known Activations