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. 4076
    Prev
    Next
    INDEX
    Explanations

    terms related to internal matters, such as internal opposition, internal medicine, internal meetings, and internal state

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "internal" in various contexts

    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
    some
    -0.86
    oÄŁ
    -0.79
    ammy
    -0.78
    kiss
    -0.73
    kson
    -0.72
    apo
    -0.71
     Parables
    -0.71
    gger
    -0.70
    enegger
    -0.70
    vich
    -0.70
    POSITIVE LOGITS
     combustion
    1.41
     workings
    1.08
    ized
    1.07
     affairs
    1.02
    ization
    0.97
    izing
    0.91
    ised
    0.90
     organs
    0.90
     strife
    0.89
     turmoil
    0.82
    Activations Density 0.030%

    No Known Activations