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. 1-RES-JB
    6. 18325
    Prev
    Next
    INDEX
    Explanations

    phrases related to official decisions or statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to formal agreements or decisions

    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
    rium
    -0.72
     McH
    -0.72
    erd
    -0.72
    ravis
    -0.69
    obin
    -0.68
    heon
    -0.68
    olls
    -0.66
    ocket
    -0.64
    opl
    -0.64
    omer
    -0.64
    POSITIVE LOGITS
     resolution
    1.45
     resolutions
    1.27
     Resolution
    1.27
     resolves
    0.94
    olution
    0.88
     resolve
    0.84
     resolving
    0.81
    resolution
    0.76
    xual
    0.73
     muster
    0.69
    Activations Density 0.008%

    No Known Activations