© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14661
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to geology and biological sciences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geological and legislative domains, particularly focusing on reports and studies

    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
    icular
    -0.78
    worn
    -0.78
    oned
    -0.76
    oning
    -0.71
    board
    -0.71
    ardless
    -0.70
    lessly
    -0.70
     tune
    -0.70
    arding
    -0.70
    holes
    -0.69
    POSITIVE LOGITS
     Affairs
    1.30
     Services
    1.14
     Forces
    1.09
     Development
    1.08
     Resources
    1.03
     Responsibility
    1.02
     Sciences
    1.02
     Intelligence
    1.01
     Investigations
    1.00
     Information
    0.99
    Activations Density 0.100%

    No Known Activations