Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22774
    Prev
    Next
    INDEX
    Explanations

    cryptocurrencies and technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    specific technological terms and keywords related to digital currencies and computing

    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
    £ı
    -0.73
    idav
    -0.65
    erk
    -0.62
    farious
    -0.61
    akable
    -0.60
    «ĺ
    -0.59
    20439
    -0.59
    £
    -0.59
    ointed
    -0.59
    pring
    -0.58
    POSITIVE LOGITS
     represents
    1.17
     is
    1.15
     isn
    1.14
     has
    1.13
     dominates
    1.11
     proponents
    1.09
     provides
    1.09
     occupies
    1.07
     exists
    1.07
     attracts
    1.06
    Activations Density 0.279%

    No Known Activations