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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2230
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms related to defining and determining conditions or violations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that define what constitutes a specific action or condition

    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
     Bald
    -0.68
    hy
    -0.67
    ying
    -0.67
    hon
    -0.64
    itch
    -0.62
    inning
    -0.60
    ITCH
    -0.60
    hner
    -0.59
    TP
    -0.58
     Bern
    -0.58
    POSITIVE LOGITS
    chnology
    0.94
    aldehyde
    0.87
    itutes
    0.87
    lehem
    0.83
    ombat
    0.81
     constitute
    0.79
    abus
    0.79
     constitutes
    0.78
    eering
    0.77
    ensibly
    0.77
    Activations Density 0.013%

    No Known Activations