© 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. 0-RES-JB
    11. 16964
    Prev
    Next
    INDEX
    Explanations

    references to and discussions about Nokia smartphones

    oai_token-act-pair · gpt-3.5-turbo

    references to specific mobile phone brands and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vae
    -0.72
    ansas
    -0.69
     Fur
    -0.69
    ares
    -0.64
    pet
    -0.62
    anches
    -0.62
     Bark
    -0.61
    ERAL
    -0.61
    ther
    -0.61
     merc
    -0.60
    POSITIVE LOGITS
     Nokia
    3.70
     Lumia
    2.38
    okia
    2.26
     BlackBerry
    2.04
     HTC
    1.72
     OnePlus
    1.68
     Xiaomi
    1.66
     handset
    1.63
     Motorola
    1.58
     Xperia
    1.57
    Activations Density 0.023%

    No Known Activations