© 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. 4-RES-JB
    11. 22059
    Prev
    Next
    INDEX
    Explanations

    references to different versions of the Android operating system

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Android operating system and its versions

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

    No Comments

    Negative Logits
    rists
    -0.89
    rier
    -0.83
    hoff
    -0.82
    ablishment
    -0.82
    ritz
    -0.78
    rikes
    -0.77
    ilts
    -0.76
    rist
    -0.75
    vernment
    -0.74
    pload
    -0.73
    POSITIVE LOGITS
    Android
    0.87
     Wear
    0.82
     Loll
    0.82
     tablets
    0.80
     phones
    0.79
     Kush
    0.78
     Tablet
    0.77
     Galaxy
    0.76
     tablet
    0.76
     Android
    0.76
    Activations Density 0.014%

    No Known Activations