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. 1-RES-JB
    6. 18083
    Prev
    Next
    INDEX
    Explanations

    Hebrew words or names, particularly related to the figure Baal

    oai_token-act-pair · gpt-3.5-turbo

    characters or words in a specific non-Latin script, particularly regarding references associated with the term "Baal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eson
    -0.84
    ipel
    -0.82
    psey
    -0.79
    steen
    -0.76
    iko
    -0.72
    ierrez
    -0.72
    onge
    -0.71
     wallets
    -0.71
    lyak
    -0.70
    ebus
    -0.69
    POSITIVE LOGITS
    Ù
    1.84
    ÙĨ
    1.80
    د
    1.77
    ا
    1.72
    Ùħ
    1.71
    ر
    1.69
    ب
    1.64
    س
    1.63
    Ùĩ
    1.61
    اØ
    1.60
    Activations Density 0.002%

    No Known Activations