© 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. 3-RES-JB
    11. 40
    Prev
    Next
    INDEX
    Explanations

    actions that involve specifying or describing something in detail

    oai_token-act-pair · gpt-3.5-turbo

    the term "specify" and its variations, indicating a focus on definitions or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pear
    -0.75
    java
    -0.70
    be
    -0.68
    bill
    -0.67
    lymp
    -0.66
    Incre
    -0.64
    nuts
    -0.64
    gart
    -0.63
    riel
    -0.63
    usc
    -0.62
    POSITIVE LOGITS
     specify
    0.78
    wcsstore
    0.77
     labels
    0.74
     wording
    0.73
    л
    0.73
    eers
    0.72
     explicitly
    0.72
    terday
    0.72
     embodiments
    0.71
     specifications
    0.70
    Activations Density 0.018%

    No Known Activations