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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 21070
    Prev
    Next
    INDEX
    Explanations

    phrases related to Australia and decentralization

    oai_token-act-pair · gpt-3.5-turbo

    references to Australian culture or characteristics

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

    No Comments

    Negative Logits
    anooga
    -0.79
    FFER
    -0.75
    éĹĺ
    -0.72
     Yankee
    -0.72
     Sawyer
    -0.66
    riad
    -0.66
    elf
    -0.66
     Jobs
    -0.65
    LER
    -0.65
     Nationwide
    -0.64
    POSITIVE LOGITS
    ogical
    1.10
    ateral
    1.02
    der
    1.01
    tarians
    0.98
    anguage
    0.96
    ogy
    0.93
    assic
    0.90
    isks
    0.89
    tarian
    0.89
    uled
    0.89
    Activations Density 0.013%

    No Known Activations