© 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. 6-RES-JB
    11. 3097
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters and global affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to significant topics or issues across various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.75
    issance
    -0.71
    vernment
    -0.64
    ilogy
    -0.63
    issan
    -0.63
    aughs
    -0.62
    ariat
    -0.62
    sson
    -0.61
    esome
    -0.61
    izons
    -0.60
    POSITIVE LOGITS
    afety
    1.02
     ranging
    0.93
    pread
    0.79
    mith
    0.76
    ensitive
    0.73
    ranging
    0.73
     like
    0.72
     resembling
    0.72
    chool
    0.71
     belonging
    0.71
    Activations Density 0.520%

    No Known Activations