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

    Neuronpedia

    Jacobian LensNEW
    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. 4919
    Prev
    Next
    INDEX
    Explanations

    phrases related to sealing or closing off something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "seal" 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
    enhagen
    -0.82
    llor
    -0.77
    icularly
    -0.73
     Drawn
    -0.68
    enegger
    -0.67
    gomery
    -0.67
    sen
    -0.67
    asma
    -0.65
    nis
    -0.63
    atana
    -0.63
    POSITIVE LOGITS
     seal
    0.93
     sealing
    0.91
     seals
    0.89
    keeper
    0.88
    wrap
    0.85
    lock
    0.85
    rets
    0.82
    recy
    0.81
    keeping
    0.81
    keepers
    0.81
    Activations Density 0.046%

    No Known Activations