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. 20281
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development, such as "dependencies"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dependencies in various contexts

    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
    past
    -0.85
    iday
    -0.85
    tell
    -0.78
    gm
    -0.78
     Athletic
    -0.72
    apers
    -0.71
    issors
    -0.71
    iman
    -0.70
    Past
    -0.69
    upper
    -0.68
    POSITIVE LOGITS
    encies
    1.25
     dependency
    1.18
     dependencies
    0.97
    ency
    0.89
     withd
    0.86
     destro
    0.86
     injection
    0.82
     coupling
    0.79
    lessly
    0.79
     headache
    0.78
    Activations Density 0.010%

    No Known Activations