© 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. 0-RES-JB
    11. 13191
    Prev
    Next
    INDEX
    Explanations

    words related to bearing a burden or having an influence on something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bearing" and its variations related to responsibility or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jess
    -0.73
    jc
    -0.71
     Unified
    -0.69
    nox
    -0.68
    audi
    -0.64
    fox
    -0.62
    atalie
    -0.62
    las
    -0.62
    ula
    -0.62
     Ek
    -0.61
    POSITIVE LOGITS
     bearing
    3.91
     Bearing
    2.16
     bearings
    1.96
    bearing
    1.85
     borne
    1.49
     carrying
    1.42
     bore
    1.33
     weighing
    1.28
     bear
    1.26
     bears
    1.13
    Activations Density 0.008%

    No Known Activations