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. 23618
    Prev
    Next
    INDEX
    Explanations

    references to specific words related to bones, including specific phrases and entities like "Skull & Bones"

    oai_token-act-pair · gpt-3.5-turbo

    references to secret societies and organizations, particularly those associated with the term "Bones."

    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
    uel
    -0.77
     lag
    -0.73
     Fernand
    -0.71
    catentry
    -0.70
    lag
    -0.68
    maxwell
    -0.68
    rero
    -0.67
    riv
    -0.64
    vent
    -0.64
    ulatory
    -0.63
    POSITIVE LOGITS
     Bones
    4.00
     Bone
    1.52
    bones
    1.47
    Bone
    1.31
     Skull
    1.27
     Spike
    1.09
     Skin
    1.05
    ansson
    1.03
     Chains
    0.95
     Malk
    0.95
    Activations Density 0.042%

    No Known Activations