© 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. 11-RES-JB
    11. 5077
    Prev
    Next
    INDEX
    Explanations

    various forms and instances of the word "vary" and its derivatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating variability or differences in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edo
    -0.68
    Ķ
    -0.67
    °
    -0.67
    oops
    -0.66
    advertising
    -0.66
    TE
    -0.65
    orio
    -0.61
    ãĥĪ
    -0.59
    ¿
    -0.59
    Bern
    -0.59
    POSITIVE LOGITS
     wildly
    1.33
     greatly
    1.28
     widely
    1.23
     considerably
    1.20
     enormously
    1.19
     markedly
    1.18
     tremendously
    1.15
     depending
    1.13
     hugely
    1.03
     dramatically
    1.02
    Activations Density 0.065%

    No Known Activations