© 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. 2-RES-JB
    11. 5341
    Prev
    Next
    INDEX
    Explanations

    phrases related to sealing or securing something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sealed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.85
    itters
    -0.68
    thus
    -0.66
    issance
    -0.65
    llor
    -0.65
    article
    -0.63
    rouse
    -0.62
    erous
    -0.62
    igel
    -0.62
    cart
    -0.61
    POSITIVE LOGITS
     sealed
    1.00
     sealing
    0.93
     seal
    0.89
    rets
    0.83
    otype
    0.81
    wrap
    0.80
    heed
    0.75
     seals
    0.75
     shut
    0.74
    nesday
    0.73
    Activations Density 0.007%

    No Known Activations