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. 4-RES-JB
    6. 17482
    Prev
    Next
    INDEX
    Explanations

    phrases related to the organization "Inter"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Inter," indicating a focus on the subject of international organizations or entities

    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
    \\\\\\\\
    -0.88
    EStream
    -0.87
    ggies
    -0.84
    ongs
    -0.84
    dylib
    -0.77
     deaf
    -0.74
    unks
    -0.73
    OHN
    -0.71
    yards
    -0.69
    \\\\\\\\\\\\\\\\
    -0.69
    POSITIVE LOGITS
    continental
    0.99
    mediate
    0.98
    medi
    0.97
    lude
    0.94
    ventions
    0.91
    sectional
    0.90
    section
    0.90
    pol
    0.90
    mitt
    0.85
    action
    0.83
    Activations Density 0.008%

    No Known Activations