© 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. 0-RES-JB
    11. 13033
    Prev
    Next
    INDEX
    Explanations

    words related to preventive actions

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to preventative measures or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umm
    -0.66
    ijn
    -0.64
    christ
    -0.64
    urch
    -0.63
     Dreams
    -0.62
     Ratings
    -0.62
    iel
    -0.61
     Devi
    -0.61
     sketches
    -0.60
     Mead
    -0.60
    POSITIVE LOGITS
     prevent
    3.17
     preventing
    2.13
     Prevent
    1.97
     prevented
    1.93
     prevents
    1.89
     avert
    1.67
     avoid
    1.65
     prevention
    1.64
     protect
    1.61
     preclude
    1.57
    Activations Density 0.015%

    No Known Activations