© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12691
    Prev
    Next
    INDEX
    Explanations

    words related to touch technology, particularly the term "Touch" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Touch" in relation to technology or products

    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
    swick
    -0.72
    assetsadobe
    -0.72
    etheless
    -0.70
    issued
    -0.67
    adiator
    -0.67
    ormal
    -0.65
     [|
    -0.62
    ousing
    -0.62
     sidx
    -0.61
    д
    -0.61
    POSITIVE LOGITS
    stones
    1.05
    stone
    0.98
    Arcade
    0.95
    downs
    0.91
    Tap
    0.84
    backs
    0.83
     Touch
    0.82
    pad
    0.79
    down
    0.79
    engers
    0.75
    Activations Density 0.009%

    No Known Activations