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. 11-RES-JB
    6. 8773
    Prev
    Next
    INDEX
    Explanations

    ages in years

    oai_token-act-pair · gpt-3.5-turbo

    references to age and the concept of being "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coord
    -0.66
    phas
    -0.65
    otin
    -0.62
    Ts
    -0.58
     conduc
    -0.57
    anyl
    -0.55
    tnc
    -0.54
     Lanka
    -0.54
    amples
    -0.53
    HUD
    -0.53
    POSITIVE LOGITS
    faced
    0.80
    digy
    0.78
     adulthood
    0.76
    years
    0.75
     infancy
    0.75
    adult
    0.72
     reincarn
    0.68
     now
    0.67
     wiser
    0.66
    Adult
    0.65
    Activations Density 0.091%

    No Known Activations