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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15880
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to measurements or population statistics

    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
    SPONSORED
    -1.02
    Community
    -0.90
    issues
    -0.89
    Unity
    -0.89
    Christmas
    -0.88
    Leaks
    -0.88
    responsible
    -0.88
    DNA
    -0.88
    Arsenal
    -0.88
    WAR
    -0.87
    POSITIVE LOGITS
     q
    1.43
     k
    1.41
     ml
    1.34
     n
    1.33
     c
    1.33
     s
    1.32
     m
    1.32
     pt
    1.32
     u
    1.31
     y
    1.30
    Activations Density 0.301%

    No Known Activations