© 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. 371
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or features of electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific item or object in the context of comparison or discussion

    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
    orate
    -0.88
    nels
    -0.84
    naires
    -0.79
    aunder
    -0.76
    umbing
    -0.75
    racial
    -0.73
    #$#$
    -0.73
    AIDS
    -0.73
    ymes
    -0.72
    ictionary
    -0.71
    POSITIVE LOGITS
     Snapdragon
    1.22
     newest
    1.12
     Xperia
    1.10
     latest
    1.09
     cheapest
    1.08
     venerable
    1.07
     GTX
    1.06
     successor
    1.03
     MacBook
    1.02
     flagship
    1.01
    Activations Density 0.192%

    No Known Activations