© 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. 4-RES-JB
    11. 7103
    Prev
    Next
    INDEX
    Explanations

    instances where something is happening just before a significant event or action

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts throughout the document

    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
    ictionary
    -0.74
     besides
    -0.71
    bourg
    -0.68
    leeve
    -0.68
    lly
    -0.67
    Iterator
    -0.65
    ATURES
    -0.65
     namely
    -0.62
     âĢº
    -0.62
    ettings
    -0.62
    POSITIVE LOGITS
     slightest
    1.34
     latter
    1.27
     onset
    1.20
     same
    1.14
     aforementioned
    1.11
     emergence
    1.06
     arrival
    1.06
     advent
    1.04
     latest
    1.00
     smallest
    0.96
    Activations Density 0.378%

    No Known Activations