Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7499
    Prev
    Next
    INDEX
    Explanations

    topics related to funding, especially when related to government, organizations, or individuals providing financial support

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with government or institutional funding

    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
     Appearance
    -0.70
    ntax
    -0.63
     syntax
    -0.63
    cheon
    -0.62
     gloves
    -0.62
     Boxing
    -0.61
     moments
    -0.60
    atter
    -0.60
     reflection
    -0.59
    dds
    -0.59
    POSITIVE LOGITS
     funded
    3.51
     financed
    2.82
    funded
    2.52
     funding
    1.93
    funding
    1.83
     Funding
    1.80
     sponsored
    1.79
    Fund
    1.70
     subsidized
    1.62
     staffed
    1.61
    Activations Density 0.015%

    No Known Activations