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. 8668
    Prev
    Next
    INDEX
    Explanations

    words related to pillars and pillars' various aspects

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with foundational concepts or structural elements

    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
    ensitivity
    -0.80
     Swanson
    -0.78
     Arduino
    -0.69
    asy
    -0.69
    hom
    -0.68
    ev
    -0.66
     Coulter
    -0.65
    azard
    -0.64
     MacBook
    -0.63
    enthal
    -0.62
    POSITIVE LOGITS
     pillar
    3.49
     pillars
    3.39
    pillar
    2.57
     Pillar
    2.14
    pill
    1.98
     cornerstone
    1.92
     Pill
    1.61
     bedrock
    1.49
     plank
    1.28
     centerpiece
    1.28
    Activations Density 0.037%

    No Known Activations