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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3955
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters with a particular emphasis on the letter "Ð"

    oai_token-act-pair · gpt-3.5-turbo

    a specific, repeated character or symbol

    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
    wagen
    -0.78
    enegger
    -0.77
    theless
    -0.75
    oleon
    -0.74
     inev
    -0.73
     Franch
    -0.71
     concede
    -0.70
     charm
    -0.70
    ierrez
    -0.65
     admission
    -0.62
    POSITIVE LOGITS
    º
    1.39
    ²
    1.31
    ¸
    1.31
    ¾
    1.28
    Ń
    1.25
    ´
    1.24
    ¹
    1.24
    ij
    1.19
    ¼
    1.19
    ¢
    1.19
    Activations Density 0.025%

    No Known Activations