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. 10-RES-JB
    6. 22045
    Prev
    Next
    INDEX
    Explanations

    uncommon special characters or formatting codes

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of specific characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    waves
    -0.61
    landish
    -0.58
     DMV
    -0.58
    heads
    -0.57
     Sidd
    -0.57
     whichever
    -0.56
     Stard
    -0.56
     gratification
    -0.56
     Catalyst
    -0.55
    fulness
    -0.55
    POSITIVE LOGITS
    ĵ
    1.72
    ¾
    1.72
    ĭ
    1.62
    ł
    1.60
    Ĵ
    1.57
    Ľ
    1.53
    ı
    1.52
    ©
    1.50
    ¼
    1.50
    ¸
    1.50
    Activations Density 0.022%

    No Known Activations