© 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. 957
    Prev
    Next
    INDEX
    Explanations

    names related to individuals with the last name "Vogelsong"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named "Vog" and "Vij."

    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
    ãĥ³ãĤ¸
    -0.88
     grease
    -0.70
    phrine
    -0.67
    ocity
    -0.66
    htaking
    -0.66
    ãĤ¨ãĥ«
    -0.65
     docks
    -0.64
    Magikarp
    -0.63
    auga
    -0.62
     Hebdo
    -0.62
    POSITIVE LOGITS
    ellen
    0.94
    ell
    0.90
    endra
    0.85
    olyn
    0.85
    dyl
    0.85
    atics
    0.84
    ey
    0.84
    edia
    0.82
    ebin
    0.82
    ean
    0.80
    Activations Density 0.065%

    No Known Activations