© 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. 6-RES-JB
    11. 17768
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "elixir"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "elixir."

    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
    ãĥ¼ãĥĨãĤ£
    -0.72
    NEY
    -0.72
    nant
    -0.70
     Crunch
    -0.67
    ãĥ´ãĤ¡
    -0.67
    LESS
    -0.64
     Analytics
    -0.63
    uyomi
    -0.62
    nces
    -0.62
     Rolls
    -0.61
    POSITIVE LOGITS
    iquid
    1.19
    izabeth
    1.18
    ibrary
    1.18
    ixir
    1.07
    usive
    1.04
    uding
    0.95
    uded
    0.92
    abor
    0.89
    ipt
    0.89
    azar
    0.87
    Activations Density 0.010%

    No Known Activations