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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3696
    Prev
    Next
    INDEX
    Explanations

    special characters and non-English alphabets with a specific emphasis on the character 'ë' and specific combinations like 'ïķ'

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or glyphs used in a non-standard encoding or script

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.83
    romeda
    -0.72
    theless
    -0.71
    ablishment
    -0.71
    bourg
    -0.70
    ambers
    -0.69
    lander
    -0.67
     Feet
    -0.67
    peed
    -0.66
    oleon
    -0.65
    POSITIVE LOGITS
    ¹
    1.08
    ª
    0.96
    º
    0.95
    ī
    0.95
    ¨
    0.93
    Ĩ
    0.93
    ķ
    0.91
    ¦
    0.91
    Į
    0.87
    Ģ
    0.87
    Activations Density 0.029%

    No Known Activations