© 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. 6-RES-JB
    11. 17086
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that the reader is currently reading something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" and its context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akable
    -0.77
    hesda
    -0.74
    chwitz
    -0.73
    asia
    -0.72
    posure
    -0.70
    htar
    -0.69
    atro
    -0.69
    aires
    -0.68
    oved
    -0.68
    Ton
    -0.67
    POSITIVE LOGITS
     aloud
    1.36
     excerpts
    0.88
     drafts
    0.84
     instructions
    0.83
     papers
    0.83
     newspapers
    0.82
     passages
    0.80
     articles
    0.79
    papers
    0.79
    é¾įå¥ij士
    0.78
    Activations Density 0.134%

    No Known Activations