© 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
    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. 18668
    Prev
    Next
    INDEX
    Explanations

    words related to sensory perceptions or sensitivities

    oai_token-act-pair · gpt-3.5-turbo

    references to sensitivity and sensuality

    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
     Kessler
    -0.71
     Carnegie
    -0.70
     Hasan
    -0.69
     Medal
    -0.67
     LINE
    -0.66
     Cody
    -0.64
     transcripts
    -0.63
     Dakota
    -0.63
     Hurricanes
    -0.62
    Disclaimer
    -0.60
    POSITIVE LOGITS
     sens
    1.21
    itized
    1.19
    ual
    1.15
    ibly
    1.14
    uality
    1.09
    itiz
    1.08
    ibility
    1.05
    uous
    1.05
    itives
    1.03
    uously
    0.99
    Activations Density 0.011%

    No Known Activations