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. 10-RES-JB
    6. 23085
    Prev
    Next
    INDEX
    Explanations

    imperative sentences telling someone to take action or make a decision

    oai_token-act-pair · gpt-3.5-turbo

    commands or suggestions to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bidden
    -0.68
    rely
    -0.68
    icons
    -0.66
     Watkins
    -0.64
    Category
    -0.59
    received
    -0.59
    developed
    -0.59
     formulas
    -0.58
     anomalies
    -0.58
     Disaster
    -0.57
    POSITIVE LOGITS
    verning
    1.05
     ahead
    1.03
     forth
    1.01
    lems
    0.99
    vt
    0.98
    ggle
    0.98
    ALK
    0.88
     forward
    0.85
     upstairs
    0.85
    oooooooo
    0.84
    Activations Density 0.067%

    No Known Activations