© 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. 1-RES-JB
    11. 4960
    Prev
    Next
    INDEX
    Explanations

    terms related to embedding or incorporating one thing into another

    oai_token-act-pair · gpt-3.5-turbo

    usages of the term "embedded" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neg
    -0.85
    amins
    -0.79
    hma
    -0.72
    quez
    -0.71
    straight
    -0.70
    uh
    -0.66
    WAYS
    -0.66
    nd
    -0.66
    arenthood
    -0.65
    anches
    -0.64
    POSITIVE LOGITS
     embedded
    1.39
    ocument
    0.99
    edded
    0.93
     cryptoc
    0.89
     embed
    0.87
     behavi
    0.84
    odied
    0.81
     arrang
    0.81
    embed
    0.78
     princ
    0.78
    Activations Density 0.010%

    No Known Activations