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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20698
    Prev
    Next
    INDEX
    Explanations

    characters with special characters and emojis

    oai_token-act-pair · gpt-3.5-turbo

    unusual or potentially coded sequences of characters, likely indicating a specific encoding or format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arton
    -0.89
    cius
    -0.78
    leground
    -0.74
    achy
    -0.73
    etsk
    -0.73
    orsche
    -0.72
     bonded
    -0.71
    iche
    -0.71
    olithic
    -0.71
    lycer
    -0.70
    POSITIVE LOGITS
    ãĤ
    1.65
    ãģ
    1.65
    ãģª
    1.50
    ãģĭ
    1.49
    ãĤī
    1.49
    ãģŁ
    1.46
    ãģĦ
    1.45
    ãĤĭ
    1.45
    ãģ¾
    1.43
    ãģ¦
    1.41
    Activations Density 0.010%

    No Known Activations