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. 10-RES-JB
    6. 23079
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth or increase over time

    oai_token-act-pair · gpt-3.5-turbo

    the word "increasingly" and its variations, indicating growth or escalation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oops
    -0.82
    halla
    -0.78
    pta
    -0.77
    ENA
    -0.74
    fen
    -0.71
    iversary
    -0.71
    rats
    -0.71
    yet
    -0.71
    ãĤ¨ãĥ«
    -0.69
    %:
    -0.69
    POSITIVE LOGITS
     reliant
    1.17
     frustrated
    1.03
     sophisticated
    1.02
     erratic
    1.02
     unpopular
    0.99
     agitated
    0.95
     prevalent
    0.95
     aggressive
    0.94
     difficult
    0.92
     polarized
    0.92
    Activations Density 0.045%

    No Known Activations