© 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. 10-RES-JB
    11. 10286
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "original."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the term "original" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utics
    -0.82
    $.
    -0.77
    their
    -0.76
    .<
    -0.75
    Ò
    -0.75
    ̶
    -0.75
    ilaterally
    -0.75
    another
    -0.73
    *.
    -0.73
    omever
    -0.72
    POSITIVE LOGITS
     motto
    1.14
     assumption
    1.12
     irony
    1.08
     analogy
    1.04
     question
    1.03
     explanation
    1.02
     implication
    1.01
     rationale
    1.00
     impetus
    1.00
     notion
    0.97
    Activations Density 0.454%

    No Known Activations