© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9041
    Prev
    Next
    INDEX
    Explanations

    special characters representing different languages

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.76
     Apollo
    -0.66
    izable
    -0.66
     decomp
    -0.65
    aimon
    -0.63
     guiActiveUnfocused
    -0.63
    ifying
    -0.61
     Bengal
    -0.60
     chrome
    -0.60
     TTL
    -0.60
    POSITIVE LOGITS
    ¬
    1.37
    ĸ
    1.34
    ĺ
    1.33
    ¼
    1.30
    ½
    1.30
    ¹
    1.29
    ľ
    1.24
    Ã
    1.23
    ļ
    1.23
    Ķ
    1.23
    Activations Density 0.003%

    No Known Activations