© 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. 4-RES-JB
    11. 1527
    Prev
    Next
    INDEX
    Explanations

    phrases related to military or defense initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to administrative divisions or political designations

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

    No Comments

    Negative Logits
    ãĤ¡
    -0.86
    terday
    -0.70
     Canaver
    -0.64
    ãĤ©
    -0.64
    Ń·
    -0.64
     pains
    -0.62
     backwards
    -0.59
    ĸļ
    -0.58
    iders
    -0.57
     htt
    -0.57
    POSITIVE LOGITS
    venture
    1.10
    vance
    1.04
    VERTIS
    1.00
    illac
    0.97
    ventures
    0.96
    visor
    0.96
    ynasty
    0.96
    DL
    0.96
    MIN
    0.95
    IUM
    0.95
    Activations Density 0.011%

    No Known Activations