© 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. 2-RES-JB
    11. 12663
    Prev
    Next
    INDEX
    Explanations

    phrases related to traffic and driving, and specifically focuses on identifying mentions of "motorists" and "shoppers" in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drivers and people shopping

    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
    ital
    -0.62
    artment
    -0.62
    ige
    -0.60
    enthal
    -0.59
     Virus
    -0.58
     srfAttach
    -0.57
     Chair
    -0.56
     mediation
    -0.56
    Chain
    -0.56
    Title
    -0.54
    POSITIVE LOGITS
    folk
    0.95
    hip
    0.90
    hips
    0.85
    paces
    0.83
    aurus
    0.82
    pread
    0.77
    autions
    0.75
    ']
    0.75
    uggest
    0.73
    rences
    0.72
    Activations Density 0.049%

    No Known Activations