© 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. 22363
    Prev
    Next
    INDEX
    Explanations

    sentences ending with one-word commands

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in various contexts

    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
    Rules
    -0.80
    upon
    -0.74
    Cho
    -0.74
    marks
    -0.72
    Conn
    -0.70
    agree
    -0.70
    Enjoy
    -0.68
    Links
    -0.66
    Att
    -0.66
    lets
    -0.66
    POSITIVE LOGITS
     sake
    1.30
     foreseeable
    1.00
     bunch
    0.94
     multitude
    0.93
     hypothetical
    0.90
     new
    0.90
     specific
    0.89
     handful
    0.88
     lot
    0.88
     purpose
    0.87
    Activations Density 0.177%

    No Known Activations