© 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. 11-RES-JB
    11. 22325
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists of phrases

    oai_token-act-pair · gpt-3.5-turbo

    commas, indicating lists or additional information within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worldly
    -0.62
    ²¾
    -0.62
    antz
    -0.61
    aughs
    -0.59
    roxy
    -0.59
    tsy
    -0.58
    ¬¼
    -0.58
    Includes
    -0.58
    EStreamFrame
    -0.56
    aceae
    -0.56
    POSITIVE LOGITS
     meanwhile
    2.05
     however
    1.75
     moreover
    1.47
     meantime
    1.31
     incidentally
    1.25
     unsurprisingly
    1.24
     furthermore
    1.19
     though
    1.15
     likewise
    1.14
     therefore
    1.12
    Activations Density 0.228%

    No Known Activations