© 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. 3-RES-JB
    11. 10763
    Prev
    Next
    INDEX
    Explanations

    references to music-related terms and software services

    oai_token-act-pair · gpt-3.5-turbo

    references to music and related technological features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oil
    -0.99
    sted
    -0.79
    stad
    -0.77
     conject
    -0.76
    arten
    -0.73
    Hart
    -0.72
    ipel
    -0.68
    illin
    -0.68
     rupt
    -0.67
     discharged
    -0.67
    POSITIVE LOGITS
     Gmail
    1.14
     Desktop
    1.07
     apps
    1.04
    Apps
    1.04
    Android
    1.04
     Xperia
    1.03
     Cortana
    1.03
     Apps
    1.03
     iCloud
    1.02
     dashboard
    1.00
    Activations Density 0.800%

    No Known Activations