© 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. 4222
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant event or moment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it was" followed by descriptive content

    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
    bies
    -0.75
     Previous
    -0.62
     Telescope
    -0.61
     Lack
    -0.60
     Current
    -0.59
     Extend
    -0.57
    edIn
    -0.57
     Examples
    -0.57
    iling
    -0.57
     Expand
    -0.56
    POSITIVE LOGITS
    nt
    0.98
     definitely
    0.92
     unclear
    0.90
    hers
    0.90
     hardly
    0.84
     abundantly
    0.82
     worth
    0.81
     also
    0.80
    Ĥİ
    0.78
    hes
    0.77
    Activations Density 0.217%

    No Known Activations