© 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. 6-RES-JB
    11. 2089
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and urgency

    oai_token-act-pair · gpt-3.5-turbo

    indicators of restrictions and conditions related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     successors
    -0.74
     sidx
    -0.69
    ohan
    -0.65
    vin
    -0.64
    artney
    -0.63
     respectively
    -0.63
    FN
    -0.62
    enegger
    -0.62
    viron
    -0.62
    ilar
    -0.62
    POSITIVE LOGITS
     scarce
    0.81
     abound
    0.78
     Freeman
    0.71
     Dove
    0.71
     instantaneous
    0.67
     understatement
    0.66
     Fuller
    0.65
     Cunningham
    0.64
     Dempsey
    0.64
    eering
    0.63
    Activations Density 0.632%

    No Known Activations