© 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 EvalsExportsinterp-engineNEWAPI 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. 11677
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of cutting or separating

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "se" appearing in various contexts

    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
    INGTON
    -0.68
    initely
    -0.67
    ington
    -0.64
     Banner
    -0.63
     admitting
    -0.62
    stown
    -0.60
     hoops
    -0.60
     diplom
    -0.59
     Uni
    -0.58
     Grimes
    -0.57
    POSITIVE LOGITS
    xt
    1.12
    perate
    1.09
    ldom
    1.06
    gue
    1.06
    xton
    1.05
    eps
    1.03
    pt
    1.02
    ptic
    1.02
    cluded
    1.01
    gments
    1.01
    Activations Density 0.019%

    No Known Activations