© 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. 4-RES-JB
    6. 22572
    Prev
    Next
    INDEX
    Explanations

    character sequences in a specific language

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols, especially those related to specific encoding formats

    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
    cules
    -0.78
     livest
    -0.75
    perse
    -0.72
     bonded
    -0.71
    wcs
    -0.70
     reconc
    -0.70
     nutrit
    -0.69
     poaching
    -0.69
     dexter
    -0.68
    owler
    -0.66
    POSITIVE LOGITS
    ÑĮ
    1.39
    ÑĢ
    1.27
    а
    1.25
    о
    1.23
    е
    1.22
    и
    1.17
    н
    1.16
    Ñģ
    1.15
    оÐ
    1.12
    в
    1.12
    Activations Density 0.007%

    No Known Activations