© 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. 11-RES-JB
    11. 7750
    Prev
    Next
    INDEX
    Explanations

    words related to actions or concepts that involve deterring, regulating, or deciding on something

    oai_token-act-pair · gpt-3.5-turbo

    words related to prevention or deterrence

    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
     appropri
    -0.60
     sucks
    -0.58
     viz
    -0.57
     HAL
    -0.56
     coworkers
    -0.55
     Haz
    -0.55
    Posts
    -0.54
     quirks
    -0.54
     subordinates
    -0.54
     seams
    -0.54
    POSITIVE LOGITS
    red
    1.67
    ered
    1.58
    ring
    1.52
    rer
    1.49
    mented
    1.44
    ted
    1.39
    ering
    1.37
    ance
    1.37
    anced
    1.35
    ant
    1.34
    Activations Density 0.439%

    No Known Activations