© 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. 5057
    Prev
    Next
    INDEX
    Explanations

    words related to a specific Mexican governor named Veracruz

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AC" or variations thereof

    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
    ĸļ
    -0.73
     Stur
    -0.73
    backer
    -0.69
    ï¸ı
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     Desire
    -0.64
     Burk
    -0.63
     Gemini
    -0.63
     Dare
    -0.63
    vironment
    -0.63
    POSITIVE LOGITS
    oustic
    1.23
    rylic
    1.18
    ademic
    1.07
    osta
    1.01
    ulum
    1.00
    rosse
    1.00
    anth
    0.98
    celer
    0.97
    ritical
    0.97
    rete
    0.93
    Activations Density 0.028%

    No Known Activations