© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10942
    Prev
    Next
    INDEX
    Explanations

    mentions of specific places or people, such as "Loews" or "Los Angeles"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lo" in various contexts

    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
    manship
    -0.96
    itated
    -0.73
    sonian
    -0.72
    ãĥĩ
    -0.71
    pillar
    -0.70
    rition
    -0.70
     Equality
    -0.69
    lished
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    chell
    -0.66
    POSITIVE LOGITS
    veland
    1.20
    fty
    1.05
    aned
    1.05
    zzle
    1.03
    oser
    1.03
    vers
    1.02
    zzi
    1.00
    pper
    0.98
    vel
    0.97
    ppy
    0.95
    Activations Density 0.017%

    No Known Activations