© 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. 10-RES-JB
    11. 2994
    Prev
    Next
    INDEX
    Explanations

    words related to actions and initiatives towards creating change or solving problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or plans aimed at improvement and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Typ
    -0.86
     Printed
    -0.84
     Writ
    -0.79
    pict
    -0.74
    Strange
    -0.73
    prints
    -0.72
    videos
    -0.70
     Proud
    -0.70
     Kubrick
    -0.70
     Sour
    -0.69
    POSITIVE LOGITS
     improve
    1.66
     mitigate
    1.65
     reduce
    1.64
     alleviate
    1.60
     strengthen
    1.56
     stabilize
    1.55
     avert
    1.54
     curb
    1.52
     stimulate
    1.50
     lessen
    1.47
    Activations Density 0.286%

    No Known Activations