© 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. 6-RES-JB
    11. 9237
    Prev
    Next
    INDEX
    Explanations

    words related to "understanding" and "knowledge"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the substring "und"

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.96
    ======
    -0.83
    ãĥīãĥ©
    -0.79
    Ò
    -0.77
    utic
    -0.76
    nect
    -0.75
     toget
    -0.69
    GY
    -0.68
    ãĤ·ãĥ£
    -0.65
    APE
    -0.64
    POSITIVE LOGITS
    erest
    1.01
    efined
    0.99
    ecided
    0.90
    oubtedly
    0.89
    lings
    0.89
    igan
    0.88
    rawn
    0.82
    oing
    0.81
    ocumented
    0.80
    ling
    0.77
    Activations Density 0.016%

    No Known Activations