© 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. 13764
    Prev
    Next
    INDEX
    Explanations

    variations of the word "versatile"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Vers" in various contexts, indicating a focus on discussions about versatility or different versions

    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
    Reviewer
    -0.80
    OPLE
    -0.73
    OWER
    -0.66
     Thumbnails
    -0.64
    heads
    -0.64
    headed
    -0.64
    older
    -0.64
    Interstitial
    -0.64
    CHR
    -0.62
    WORK
    -0.61
    POSITIVE LOGITS
    atile
    1.68
    atility
    1.49
    ions
    1.09
    arial
    1.03
    ationally
    0.98
    ioned
    0.96
    ation
    0.95
    aries
    0.94
    ilage
    0.93
    alis
    0.93
    Activations Density 0.029%

    No Known Activations