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. 6-RES-JB
    6. 15609
    Prev
    Next
    INDEX
    Explanations

    patterns of characters that do not form recognizable words or phrases, potentially related to noise or coding errors

    oai_token-act-pair · gpt-3.5-turbo

    specific character sequences or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighed
    -0.91
    iscal
    -0.82
    idges
    -0.75
    igon
    -0.75
    oche
    -0.74
    iche
    -0.72
    cients
    -0.72
     Phi
    -0.70
     Siem
    -0.69
    elsen
    -0.69
    POSITIVE LOGITS
    ãģ
    1.26
    ãĤī
    1.20
    ãĤĮ
    1.17
    ãģĭ
    1.14
    ãĤĭ
    1.13
    ãģĵ
    1.10
    ãģĦ
    1.06
    ãĤ
    1.06
    ãģ£
    1.05
    ãģķ
    1.05
    Activations Density 0.014%

    No Known Activations