© 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. 6-RES-JB
    11. 4402
    Prev
    Next
    INDEX
    Explanations

    actions related to undergoing some form of treatment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    the term "undergo" and its variations, indicating processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wi
    -0.78
    cube
    -0.71
    ****************
    -0.68
    empty
    -0.65
    lua
    -0.64
    rug
    -0.63
    spir
    -0.62
     franc
    -0.61
    AW
    -0.60
     Liberals
    -0.59
    POSITIVE LOGITS
     undergone
    0.99
    uberty
    0.88
     undergo
    0.85
     surgery
    0.82
     transformations
    0.79
    ospital
    0.77
    metic
    0.75
     periodic
    0.74
     puberty
    0.74
     renovations
    0.74
    Activations Density 0.022%

    No Known Activations