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. 7569
    Prev
    Next
    INDEX
    Explanations

    economic or financial terms or expressions

    oai_token-act-pair · gpt-3.5-turbo

    strings of characters resembling special 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
    creen
    -0.72
     shroud
    -0.71
     kindergarten
    -0.70
     blanket
    -0.70
     board
    -0.68
    enegger
    -0.68
     womb
    -0.65
     messenger
    -0.65
     impart
    -0.64
     bombard
    -0.62
    POSITIVE LOGITS
    ł
    1.53
    ¹
    1.37
    ª
    1.34
    ij
    1.30
    ı
    1.29
    IJ
    1.29
    į
    1.21
    ³
    1.19
    £
    1.19
    Ĵ
    1.18
    Activations Density 0.114%

    No Known Activations