© 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. 8-RES-JB
    11. 12346
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to a certain location or organization named "Ord"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or entity named "Ord" along with related terms associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĨãĤ£
    -0.77
    ãĤ©
    -0.70
    ted
    -0.68
    etsk
    -0.68
    Shock
    -0.66
    pson
    -0.64
     sclerosis
    -0.64
    peria
    -0.62
    ãĤ£
    -0.61
    ãĤ¬
    -0.61
    POSITIVE LOGITS
    nance
    1.40
    inance
    1.26
    inances
    1.21
    inarily
    1.18
    eal
    1.09
    inary
    1.05
    eals
    0.94
    aining
    0.91
    ained
    0.90
    ered
    0.89
    Activations Density 0.050%

    No Known Activations