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. 4-RES-JB
    6. 5394
    Prev
    Next
    INDEX
    Explanations

    phrases related to pyramids

    oai_token-act-pair · gpt-3.5-turbo

    references to pyramids or pyramid-like structures

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

    No Comments

    Negative Logits
    ãĤī
    -0.82
    BAT
    -0.81
     Kers
    -0.79
    ties
    -0.77
     Dragonbound
    -0.75
    cedented
    -0.75
    ãģ¦
    -0.75
    held
    -0.74
    ãģĹ
    -0.72
    ãĤĬ
    -0.72
    POSITIVE LOGITS
    ramids
    1.27
     pyramid
    1.21
    ramid
    1.05
     Pyramid
    0.79
    ongyang
    0.76
     plateau
    0.74
     shaped
    0.72
    hedral
    0.70
     complexes
    0.69
    omet
    0.68
    Activations Density 0.010%

    No Known Activations