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

    Neuronpedia

    Jacobian LensNEW
    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. 20693
    Prev
    Next
    INDEX
    Explanations

    repetitive or ongoing actions and statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express continuity or persistent actions

    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
    sonian
    -0.98
    orthy
    -0.82
    KEN
    -0.79
    atana
    -0.74
    entin
    -0.74
    ooter
    -0.72
    halla
    -0.70
    tainment
    -0.70
    acus
    -0.69
    bis
    -0.69
    POSITIVE LOGITS
     popping
    1.14
     repeating
    1.13
     bothering
    1.02
     piling
    1.01
     slipping
    0.98
     pace
    0.97
     evolving
    0.97
     coming
    0.97
     churn
    0.96
     reminding
    0.94
    Activations Density 0.059%

    No Known Activations