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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23555
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and associated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     roy
    -0.18
     Hebdo
    -0.18
    ÄŁ
    -0.18
     appell
    -0.16
    âĢ
    -0.16
    âĢİ
    -0.16
     thus
    -0.16
     diplom
    -0.16
     Ãĸ
    -0.16
    eers
    -0.16
    POSITIVE LOGITS
    ActionCode
    0.32
    ThumbnailImage
    0.31
    	
    0.31
    ú
    0.31
    ø
    0.31
    ü
    0.31
    À
    0.31
    Ĝ
    0.31
    Č
    0.31
    ă
    0.31
    Activations Density 5.761%

    No Known Activations