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. 2182
    Prev
    Next
    INDEX
    Explanations

    terms related to stability or things being stable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stable."

    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
    hig
    -0.86
    vernment
    -0.80
    ulhu
    -0.75
     appealed
    -0.75
    tein
    -0.73
    FactoryReloaded
    -0.71
    atche
    -0.71
    externalActionCode
    -0.71
    printed
    -0.70
    uania
    -0.70
    POSITIVE LOGITS
     isot
    1.00
     stable
    0.94
     equilibrium
    0.84
    mate
    0.84
    iable
    0.83
     stability
    0.82
    mates
    0.79
     Stability
    0.78
     fixture
    0.77
     fry
    0.77
    Activations Density 0.005%

    No Known Activations