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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 22073
    Prev
    Next
    INDEX
    Explanations

    the term "heavy" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    terms related to heaviness or significant weight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    vous
    -0.84
    DEV
    -0.76
     Unlimited
    -0.73
    SPONSORED
    -0.73
    ilant
    -0.69
    urated
    -0.68
    icho
    -0.68
    mberg
    -0.67
    isphere
    -0.66
    HCR
    -0.66
    POSITIVE LOGITS
    weights
    1.69
     hitters
    1.34
    weight
    1.27
     hitter
    1.19
     duty
    1.16
     lifting
    1.15
    duty
    1.05
     metals
    0.98
     weights
    0.92
     reliance
    0.91
    Activations Density 0.028%

    No Known Activations