© 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. 2-RES-JB
    11. 17875
    Prev
    Next
    INDEX
    Explanations

    mentions of specific smartphone brands such as OnePlus and Xiaomi

    oai_token-act-pair · gpt-3.5-turbo

    specific brands or model names of technology products, particularly smartphones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    binding
    -0.78
    mingham
    -0.78
    enance
    -0.78
    HCR
    -0.76
    dropping
    -0.73
    tle
    -0.73
    tainment
    -0.72
    stood
    -0.70
    afia
    -0.66
    ERAL
    -0.66
    POSITIVE LOGITS
     OnePlus
    1.11
    aurus
    0.76
    Pixel
    0.74
    Lens
    0.73
    ctr
    0.70
     Xiaomi
    0.67
    nect
    0.66
    fen
    0.65
     enclosure
    0.64
     coils
    0.64
    Activations Density 0.006%

    No Known Activations