© 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. 961
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or physical actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the expression "going out," particularly in relation to actions or situations

    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
     pertinent
    -0.61
     Applic
    -0.61
     Pearce
    -0.57
     impending
    -0.55
     suffice
    -0.55
    Applic
    -0.54
    enance
    -0.54
    ilies
    -0.54
     recovered
    -0.54
    ________________
    -0.53
    POSITIVE LOGITS
    wagon
    0.87
     unnoticed
    0.86
    zag
    0.86
     overboard
    0.86
    nova
    0.85
     route
    0.80
     undefeated
    0.77
     unch
    0.75
    estyle
    0.75
     sidx
    0.74
    Activations Density 0.138%

    No Known Activations