© 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. 7-RES-JB
    11. 9474
    Prev
    Next
    INDEX
    Explanations

    words related to performing activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to complaints and frustrations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.72
    apter
    -0.71
    ophon
    -0.66
    è£ħ
    -0.64
    uthor
    -0.60
    hene
    -0.60
     Shak
    -0.59
     forthcoming
    -0.57
     previously
    -0.57
     concluded
    -0.57
    POSITIVE LOGITS
     everyday
    0.87
     regularly
    0.86
     nowadays
    0.85
     differently
    0.84
     yearly
    0.83
    ometimes
    0.82
     daily
    0.82
     weekly
    0.78
     whenever
    0.77
    every
    0.75
    Activations Density 0.885%

    No Known Activations