© 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. 4-RES-JB
    11. 4836
    Prev
    Next
    INDEX
    Explanations

    Russian words written in a Cyrillic script

    oai_token-act-pair · gpt-3.5-turbo

    Cyrillic characters primarily used in the Serbian language

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

    No Comments

    Negative Logits
     Starr
    -0.80
    atche
    -0.74
    otle
    -0.72
    ttes
    -0.69
     Gutenberg
    -0.68
    ulhu
    -0.66
     Johannes
    -0.65
     Wiley
    -0.64
    olkien
    -0.64
     McMaster
    -0.64
    POSITIVE LOGITS
    ÑĤ
    1.17
    к
    1.11
    Ñģ
    0.95
    л
    0.94
    и
    0.92
    оÐ
    0.89
    ¿
    0.88
    н
    0.87
    dimension
    0.87
    м
    0.85
    Activations Density 0.011%

    No Known Activations