© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17421
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that do not correspond to any meaningful language or pattern

    oai_token-act-pair · gpt-3.5-turbo

    Cyrillic characters or words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Joy
    -0.73
    auga
    -0.73
    terson
    -0.71
     Spur
    -0.66
    ichita
    -0.64
    higher
    -0.63
    BIL
    -0.63
    creen
    -0.62
    cence
    -0.61
    ndra
    -0.61
    POSITIVE LOGITS
    оÐ
    1.34
    и
    1.28
    Ñĥ
    1.27
    а
    1.26
    о
    1.25
    е
    1.21
    ÑĮ
    1.00
    Ñĭ
    1.00
    ×Ļ×
    0.99
    н
    0.98
    Activations Density 0.018%

    No Known Activations