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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 17210
    Prev
    Next
    INDEX
    Explanations

    sentences ending with either a period or a specific symbol

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong negative sentiments or highlight distressing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilibrium
    -0.77
     organis
    -0.76
    omics
    -0.74
     envis
    -0.72
    itably
    -0.71
     compositions
    -0.69
    ikuman
    -0.69
     conceptual
    -0.69
     grouping
    -0.69
     computing
    -0.67
    POSITIVE LOGITS
     Their
    1.05
     They
    1.05
     Says
    0.96
     Meanwhile
    0.95
     Residents
    0.94
     Shame
    0.90
     Families
    0.90
     Parents
    0.89
     Pict
    0.86
     Especially
    0.85
    Activations Density 0.979%

    No Known Activations