© 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. 4-RES-JB
    11. 6389
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rules or regulations

    oai_token-act-pair · gpt-3.5-turbo

    the word "shall" indicating legal or formal obligations

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

    No Comments

    Negative Logits
     Advertisement
    -0.77
    cule
    -0.73
    serving
    -0.67
    enthal
    -0.66
    Cop
    -0.64
    packing
    -0.64
     Arena
    -0.63
    activated
    -0.62
     Closing
    -0.61
    TT
    -0.61
    POSITIVE LOGITS
    ower
    0.96
     hereafter
    0.92
     endeavour
    0.87
     be
    0.87
    ghai
    0.84
     gladly
    0.82
    otle
    0.80
    ajor
    0.79
     surely
    0.78
     suffice
    0.78
    Activations Density 0.012%

    No Known Activations