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. 0-RES-JB
    6. 60
    Prev
    Next
    INDEX
    Explanations

    words related to padding or cushioning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to protective padding or pads used in various contexts

    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
     Ernst
    -0.72
    Aust
    -0.72
     elections
    -0.69
     Religion
    -0.68
     Classification
    -0.67
     Taxes
    -0.66
     Volunte
    -0.66
    Albert
    -0.66
     Cosponsors
    -0.65
    Emer
    -0.65
    POSITIVE LOGITS
     pad
    4.01
     pads
    3.46
    pad
    2.33
     Pad
    2.02
    Pad
    1.70
     padding
    1.26
     padded
    1.25
     mats
    1.19
     pedal
    0.98
     cushion
    0.92
    Activations Density 0.015%

    No Known Activations