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. 21401
    Prev
    Next
    INDEX
    Explanations

    Japanese characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and their variations

    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
    hyde
    -0.98
     circulation
    -0.80
    gdala
    -0.79
    opsy
    -0.75
    ysis
    -0.74
    omorphic
    -0.73
    iffe
    -0.72
     visitation
    -0.72
     plateau
    -0.71
    geries
    -0.71
    POSITIVE LOGITS
    ÙĨ
    1.07
    ï¸
    1.06
    æľ
    1.02
    ×ķ
    1.01
    ÙĦ
    0.98
    è¯
    0.94
    Xi
    0.94
    ÙIJ
    0.93
    ãĤī
    0.93
    ת
    0.91
    Activations Density 0.008%

    No Known Activations