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. 8122
    Prev
    Next
    INDEX
    Explanations

    financial transactions or high-value exchanges

    oai_token-act-pair · gpt-3.5-turbo

    repeated symbols or characters, specifically focusing on variations involving the character "âĢ."

    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
    etsy
    -0.70
    romy
    -0.70
     minim
    -0.70
     scatter
    -0.66
    olean
    -0.63
    enta
    -0.62
     remed
    -0.62
    ussian
    -0.61
     nod
    -0.61
     dig
    -0.60
    POSITIVE LOGITS
    âĹ¼
    0.87
    ISIS
    0.85
    drivers
    0.83
    âĢł
    0.79
    catentry
    0.79
    âģ
    0.78
    ¹
    0.78
    §
    0.76
    Spons
    0.76
    Ī
    0.75
    Activations Density 0.451%

    No Known Activations