© 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. 10-RES-JB
    11. 20531
    Prev
    Next
    INDEX
    Explanations

    words related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    significant actions or processes related to change or transformation

    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
    Its
    -0.67
     Bah
    -0.65
    Cub
    -0.65
     Its
    -0.64
    rican
    -0.59
     believes
    -0.58
     Bron
    -0.58
     Diane
    -0.57
    atform
    -0.57
    Watch
    -0.56
    POSITIVE LOGITS
     themselves
    1.56
     prolifer
    1.02
     their
    0.97
     individually
    0.94
    selves
    0.94
    their
    0.89
     respectively
    0.88
     respective
    0.87
     counterparts
    0.87
     varying
    0.84
    Activations Density 0.656%

    No Known Activations