Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 18205
    Prev
    Next
    INDEX
    Explanations

    specific model names of Sony Xperia phones

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products or brands, particularly related to Sony's Xperia line

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zees
    -0.79
    ety
    -0.73
    nington
    -0.71
    Reviewer
    -0.70
    zee
    -0.69
    iddles
    -0.67
    lyn
    -0.67
    uine
    -0.67
    Bir
    -0.66
    apult
    -0.66
    POSITIVE LOGITS
    imation
    0.98
     localized
    0.94
    oÄŁ
    0.92
     Xperia
    0.79
    ricanes
    0.77
     Ion
    0.76
     tremend
    0.75
    oice
    0.72
    raviolet
    0.70
    ailability
    0.70
    Activations Density 0.009%

    No Known Activations