© 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. 10-RES-JB
    11. 8600
    Prev
    Next
    INDEX
    Explanations

    shortened versions of the word "embedded"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Embed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.85
    gers
    -0.75
    ãĥĥãĥĪ
    -0.71
     è£ı
    -0.69
    姫
    -0.68
    culosis
    -0.68
    ãĥīãĥ©
    -0.68
     obsc
    -0.64
    creen
    -0.62
    ãĥ¼ãĥĨ
    -0.61
    POSITIVE LOGITS
    arrass
    1.44
    edded
    1.37
    odied
    1.28
    assies
    1.16
    argo
    1.12
    assy
    1.09
    attled
    1.09
    edd
    1.07
    odies
    0.99
    olicy
    0.93
    Activations Density 0.032%

    No Known Activations