© 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. 4-RES-JB
    11. 1432
    Prev
    Next
    INDEX
    Explanations

    important or decisive words and phrases, especially those related to critical junctures or key moments in a context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant moments or decisions

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

    No Comments

    Negative Logits
    ander
    -0.80
    á
    -0.78
    folk
    -0.73
    nery
    -0.72
    employment
    -0.72
    False
    -0.72
    alsh
    -0.70
    incarn
    -0.69
    eming
    -0.68
    amm
    -0.68
    POSITIVE LOGITS
    onite
    0.90
    wcs
    0.87
     pivotal
    0.86
     importance
    0.85
     swing
    0.84
     crucial
    0.81
     jun
    0.81
     battleground
    0.80
     hinge
    0.80
     reversal
    0.76
    Activations Density 0.025%

    No Known Activations