© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21683
    Prev
    Next
    INDEX
    Explanations

    edits or updates made to a piece of content

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "edit" in a document

    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
     Leone
    -0.71
     Jindal
    -0.69
     Limbaugh
    -0.60
     ambul
    -0.60
     Parks
    -0.60
     Newt
    -0.59
     Tuls
    -0.59
     Yug
    -0.58
     Incarn
    -0.58
     Luxem
    -0.57
    POSITIVE LOGITS
    ors
    1.13
    orship
    1.13
    ipedia
    0.99
    ored
    0.89
    itors
    0.87
    endum
    0.85
    rator
    0.84
    ional
    0.83
    edit
    0.81
    esty
    0.81
    Activations Density 0.026%

    No Known Activations