© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12857
    Prev
    Next
    INDEX
    Explanations

    terms related to competitions or disputes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contested or disputed situations, particularly in political or territorial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erie
    -0.82
    resa
    -0.80
    ugen
    -0.79
    abet
    -0.76
    License
    -0.73
    of
    -0.73
    aret
    -0.72
    eno
    -0.72
    aryn
    -0.72
    tra
    -0.71
    POSITIVE LOGITS
     disputed
    0.97
     contested
    0.91
     hotly
    0.76
     ground
    0.74
     territories
    0.73
     battleground
    0.71
     acres
    0.66
     fields
    0.64
    roversial
    0.62
     surfaces
    0.62
    Activations Density 0.013%

    No Known Activations