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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3294
    Prev
    Next
    INDEX
    Explanations

    mentions of tablets, especially in the context of technology and devices

    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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.86
    ^^^^
    -0.77
    atorium
    -0.71
    ãģį
    -0.70
    anchester
    -0.69
     Kn
    -0.68
    é»Ĵ
    -0.66
    utherford
    -0.66
     repr
    -0.64
    ãĥ£
    -0.64
    POSITIVE LOGITS
     Tablet
    1.01
     tablets
    0.96
     tablet
    0.93
     PCs
    0.90
    devices
    0.82
    izen
    0.81
    icals
    0.75
    agra
    0.74
     Devices
    0.73
    iph
    0.69
    Activations Density 0.012%

    No Known Activations