© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6207
    Prev
    Next
    INDEX
    Explanations

    mentions of specific Apple products, specifically iPhones and iPods

    oai_token-act-pair · gpt-3.5-turbo

    references to specific iPhone and iPod models

    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
    ndra
    -0.81
    bil
    -0.80
    rans
    -0.79
    nant
    -0.77
    committee
    -0.76
    rha
    -0.75
    é¾
    -0.75
    hirt
    -0.75
    hips
    -0.74
    mingham
    -0.73
    POSITIVE LOGITS
     iPad
    0.93
     Apps
    0.90
     Simulator
    0.90
     iCloud
    0.87
     iTunes
    0.84
     Safari
    0.83
    iOS
    0.83
     SDK
    0.82
     X
    0.82
     iPhone
    0.81
    Activations Density 0.021%

    No Known Activations