© 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. 7-RES-JB
    11. 4967
    Prev
    Next
    INDEX
    Explanations

    sentences ending with some form of punctuation

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ishable
    -0.78
     seamless
    -0.72
    poral
    -0.72
     transition
    -0.70
     efficiently
    -0.70
     uninterrupted
    -0.69
     undet
    -0.69
     moth
    -0.68
    breaker
    -0.68
     relic
    -0.68
    POSITIVE LOGITS
     Others
    1.46
     Their
    1.22
    Others
    1.20
     They
    1.18
     Critics
    1.10
     Some
    1.05
     Especially
    1.04
     Perhaps
    0.99
     Particularly
    0.96
     Many
    0.96
    Activations Density 0.635%

    No Known Activations