© 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. 9-RES-JB
    6. 17324
    Prev
    Next
    INDEX
    Explanations

    foreign words written in Cyrillic script

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases in Slavic languages or references to notable cultural aspects related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aram
    -0.71
    abase
    -0.63
    osponsors
    -0.60
     stub
    -0.59
    ateurs
    -0.58
    leness
    -0.58
     horr
    -0.57
    raped
    -0.57
     veterinarian
    -0.57
    orers
    -0.56
    POSITIVE LOGITS
    Ń·
    0.84
    Unix
    0.82
    imaru
    0.77
     Janeiro
    0.75
    nik
    0.71
    insky
    0.70
     Radiation
    0.68
    ãĥĩ
    0.66
    æł
    0.66
    Ð
    0.66
    Activations Density 0.370%

    No Known Activations