© 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. 7-RES-JB
    11. 23858
    Prev
    Next
    INDEX
    Explanations

    words related to acts of cutting or separation

    oai_token-act-pair · gpt-3.5-turbo

    references to "cut" in various contexts

    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
     Grace
    -0.70
    issance
    -0.68
     Moder
    -0.68
     Directorate
    -0.66
    AMP
    -0.65
    ively
    -0.63
     Kamp
    -0.63
    BUS
    -0.63
     Amon
    -0.61
    agher
    -0.60
    POSITIVE LOGITS
    scene
    1.45
    scenes
    1.37
    lasses
    1.29
    thro
    1.29
    aneous
    1.21
    lass
    1.19
    tle
    1.08
    away
    1.08
    aways
    1.06
    offs
    1.04
    Activations Density 0.031%

    No Known Activations