© 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. 9-RES-JB
    11. 17771
    Prev
    Next
    INDEX
    Explanations

    words related to deteriorating or negative situations

    oai_token-act-pair · gpt-3.5-turbo

    words or terms related to issues impacting systems and structures

    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
     dressing
    -0.70
     donating
    -0.64
     aisle
    -0.64
     stewards
    -0.64
     secretaries
    -0.62
     praying
    -0.62
     listening
    -0.61
     submission
    -0.60
     cabinet
    -0.60
    Kit
    -0.60
    POSITIVE LOGITS
    ould
    0.95
    ounded
    0.94
    etheless
    0.93
    ersed
    0.93
    ceed
    0.91
    ifies
    0.90
    elled
    0.87
    shed
    0.85
    ounced
    0.85
    alysed
    0.84
    Activations Density 0.164%

    No Known Activations