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. 3-RES-JB
    6. 8542
    Prev
    Next
    INDEX
    Explanations

    mentions of smallness or entities with "Small" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Small" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.76
    ++++++++++++++++
    -0.70
    ILLE
    -0.67
     largeDownload
    -0.66
    çīĪ
    -0.66
    aline
    -0.66
    vironment
    -0.65
     eminent
    -0.65
    naissance
    -0.65
    NSA
    -0.64
    POSITIVE LOGITS
    pox
    1.05
     intestine
    0.91
     fry
    0.89
     batches
    0.83
     sized
    0.82
     consolation
    0.80
     scale
    0.79
     (<
    0.78
     increments
    0.77
    hearted
    0.76
    Activations Density 0.025%

    No Known Activations