© 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. 10-RES-JB
    6. 8436
    Prev
    Next
    INDEX
    Explanations

    terms related to elephants and ivory

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lly
    -0.79
    cation
    -0.74
     Brewer
    -0.73
    ername
    -0.72
    mble
    -0.71
    naissance
    -0.70
    lis
    -0.70
     McDonnell
    -0.69
     macOS
    -0.68
    HER
    -0.67
    POSITIVE LOGITS
    iasis
    1.19
     elephant
    1.08
     elephants
    1.06
     Haram
    1.05
     ivory
    1.00
     poaching
    1.00
    opard
    0.94
    ota
    0.90
     herds
    0.88
     Elephant
    0.85
    Activations Density 0.061%

    No Known Activations