© 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. 7891
    Prev
    Next
    INDEX
    Explanations

    references to mobile app stores, particularly Google Play Store

    oai_token-act-pair · gpt-3.5-turbo

    references to app stores and digital services related to Google

    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
     needle
    -0.69
     muzzle
    -0.66
     spe
    -0.65
     theoret
    -0.64
     whistle
    -0.64
    othy
    -0.64
     chamber
    -0.64
     dagger
    -0.62
     Kurd
    -0.62
    nian
    -0.62
    POSITIVE LOGITS
     Services
    0.93
     Finder
    0.85
     Server
    0.84
     SDK
    0.84
     Manager
    0.82
    Shop
    0.81
     Apps
    0.80
     Console
    0.79
    merce
    0.79
     Movies
    0.78
    Activations Density 0.165%

    No Known Activations