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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 17745
    Prev
    Next
    INDEX
    Explanations

    words related to tombs, such as "tombs" itself and related terms like "pyramids" and "bones."

    oai_token-act-pair · gpt-3.5-turbo

    words related to tombs and burial practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parent
    -0.78
     Education
    -0.74
    ainer
    -0.72
     Heard
    -0.69
     Polaris
    -0.69
    iga
    -0.68
     Bever
    -0.66
     Hanson
    -0.64
     Gloss
    -0.64
     Rain
    -0.64
    POSITIVE LOGITS
     tom
    4.14
     tomb
    1.37
    tom
    1.35
     py
    1.15
     graves
    1.07
     tim
    1.04
     bom
    1.04
     mummy
    1.01
     sam
    0.98
     phantom
    0.98
    Activations Density 0.017%

    No Known Activations