© 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. 0-RES-JB
    11. 9522
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of something being deeply set or fixed within something else

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of "embedding" in various contexts

    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
     Races
    -0.72
    ittee
    -0.67
    ilee
    -0.67
    quire
    -0.67
     Franklin
    -0.66
    iest
    -0.66
    pri
    -0.66
    wit
    -0.65
    morrow
    -0.65
     fortun
    -0.65
    POSITIVE LOGITS
     embedded
    3.68
     embed
    2.40
    embed
    1.98
    edded
    1.54
     implanted
    1.50
     attached
    1.46
     ingrained
    1.41
     integrated
    1.27
     intertwined
    1.27
     entrenched
    1.26
    Activations Density 0.019%

    No Known Activations