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. 22613
    Prev
    Next
    INDEX
    Explanations

    references to individuals with specialized roles or expertise, particularly in law enforcement and government

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Special" 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
    •Special

    No Comments

    Negative Logits
    amus
    -0.74
    shown
    -0.69
    Į
    -0.64
    yard
    -0.63
    hari
    -0.63
    bane
    -0.63
    latest
    -0.62
    OTAL
    -0.62
     Decay
    -0.62
    asus
    -0.61
    POSITIVE LOGITS
    ised
    1.26
    ties
    1.21
    izations
    1.20
    isations
    1.13
    ized
    0.99
    ises
    0.97
     relativity
    0.97
    ities
    0.95
    ity
    0.95
    isation
    0.94
    Activations Density 0.042%

    No Known Activations