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. 3-RES-JB
    6. 10323
    Prev
    Next
    INDEX
    Explanations

    mentions of electronic devices, specifically tablets

    oai_token-act-pair · gpt-3.5-turbo

    references to tablets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -1.03
    anchester
    -0.75
    ^^^^
    -0.73
    ãģį
    -0.69
    ETA
    -0.68
    ãĥ£
    -0.68
    é»Ĵ
    -0.67
    ãĤ±
    -0.65
    utherford
    -0.64
    phe
    -0.63
    POSITIVE LOGITS
     tablets
    1.11
     tablet
    1.09
     Tablet
    1.06
     PCs
    0.92
    icals
    0.79
     Devices
    0.77
    izen
    0.75
     devices
    0.72
    devices
    0.72
    tops
    0.71
    Activations Density 0.009%

    No Known Activations