© 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. 12470
    Prev
    Next
    INDEX
    Explanations

    words related to actions, often involving two or more parties or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "both" and its usage in contrasting or comparing different aspects or entities

    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
    odore
    -0.78
    hibition
    -0.67
     Syndrome
    -0.66
     Caption
    -0.65
    erest
    -0.63
    agne
    -0.62
     syndrome
    -0.61
     Pastebin
    -0.61
     slideshow
    -0.61
    ahime
    -0.59
    POSITIVE LOGITS
     domestically
    1.12
     orally
    1.12
     indoors
    1.09
     externally
    1.06
     physically
    1.05
     verbally
    1.04
     individually
    1.03
     internally
    1.02
     horizontally
    1.00
     locally
    0.97
    Activations Density 0.093%

    No Known Activations