© 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. 7-RES-JB
    11. 20590
    Prev
    Next
    INDEX
    Explanations

    actions or events that happen before another specific action or event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence of events or actions that occur prior to another action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.91
    hack
    -0.78
    oret
    -0.72
    DO
    -0.72
    ISM
    -0.71
    ische
    -0.70
    Force
    -0.69
    JV
    -0.69
    amount
    -0.69
    venture
    -0.67
    POSITIVE LOGITS
     settling
    0.95
     disappearing
    0.94
     realizing
    0.92
     fading
    0.92
     returning
    0.92
     retiring
    0.91
     embark
    0.91
     piv
    0.87
     abruptly
    0.86
     retreating
    0.85
    Activations Density 0.056%

    No Known Activations