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. 4-RES-JB
    6. 5307
    Prev
    Next
    INDEX
    Explanations

    Italian words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly those indicating sections or items within a list or document

    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
    ierrez
    -0.93
    ichick
    -0.91
    awei
    -0.86
    phis
    -0.86
    eatures
    -0.84
    pedia
    -0.83
    icz
    -0.81
    olicited
    -0.81
    undai
    -0.81
    axies
    -0.80
    POSITIVE LOGITS
    ر
    0.92
    اÙĦ
    0.89
    Ùĩ
    0.86
    ÙĬ
    0.85
    ÙĨ
    0.82
    ÙĴ
    0.82
    ÙIJ
    0.81
    ع
    0.79
     Centauri
    0.77
    ãĥł
    0.77
    Activations Density 0.014%

    No Known Activations