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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2-RES-JB
    6. 16257
    Prev
    Next
    INDEX
    Explanations

    mentions of things related to the term "Heavy"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'heavy' topics or concepts, particularly in the context of industries or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifice
    -0.82
    UTION
    -0.74
    nesota
    -0.74
    é»Ĵ
    -0.74
     quo
    -0.73
    HCR
    -0.72
    ipt
    -0.71
    posted
    -0.70
     externalToEVAOnly
    -0.69
    à
    -0.68
    POSITIVE LOGITS
    weight
    1.11
    weights
    1.05
     Duty
    1.02
    metal
    0.87
     duty
    0.82
    ener
    0.81
    pants
    0.79
     Worker
    0.78
     Metal
    0.77
    storms
    0.75
    Activations Density 0.011%

    No Known Activations