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. 9-RES-JB
    6. 15155
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research and experiments

    oai_token-act-pair · gpt-3.5-turbo

    scientific terminology related to biochemical processes and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atism
    -0.93
    abouts
    -0.82
    minist
    -0.74
    offic
    -0.70
    ileaks
    -0.67
    ustom
    -0.66
    arde
    -0.65
     wardrobe
    -0.65
    aus
    -0.64
    roman
    -0.63
    POSITIVE LOGITS
    Researchers
    1.10
    Explore
    1.03
    Scientists
    0.98
     Researchers
    0.88
     researchers
    0.85
    Professor
    0.84
     Scientists
    0.83
    RESULTS
    0.81
     researcher
    0.80
    Abstract
    0.79
    Activations Density 0.247%

    No Known Activations