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. 4-RES-JB
    6. 21330
    Prev
    Next
    INDEX
    Explanations

    words related to demotion

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "demotion" and related terms indicating decline or reduction in status

    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
    WAYS
    -0.85
    gerald
    -0.70
    lihood
    -0.69
    tis
    -0.68
    URN
    -0.66
    DAY
    -0.65
     Aid
    -0.65
    Pull
    -0.65
    FORE
    -0.65
     Wonderland
    -0.64
    POSITIVE LOGITS
    agogue
    1.16
    agog
    1.13
    ilit
    1.05
    igration
    1.00
    ographically
    1.00
    onym
    0.99
    otions
    0.99
    ploy
    0.92
    onse
    0.90
    aterial
    0.89
    Activations Density 0.008%

    No Known Activations