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. 2-RES-JB
    6. 3477
    Prev
    Next
    INDEX
    Explanations

    words related to weight

    oai_token-act-pair · gpt-3.5-turbo

    mentions of weight

    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
     Brist
    -0.78
     Mb
    -0.77
     VIS
    -0.75
     Suc
    -0.74
     Noir
    -0.73
     Jobs
    -0.71
    BLE
    -0.70
     Fellow
    -0.68
     TEAM
    -0.68
     Rap
    -0.67
    POSITIVE LOGITS
     weight
    1.12
     weights
    1.10
    weight
    1.05
    lifting
    1.02
    Weight
    0.99
     weigh
    0.94
    weights
    0.91
     burden
    0.87
     heavier
    0.86
     burdens
    0.86
    Activations Density 0.011%

    No Known Activations