© 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. 6901
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters related specifically to the letter "о"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    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
     Clover
    -0.87
    esville
    -0.86
    nesday
    -0.85
    raints
    -0.84
    ologically
    -0.80
    ometimes
    -0.79
    ruciating
    -0.75
    mble
    -0.74
    secut
    -0.73
     GOODMAN
    -0.72
    POSITIVE LOGITS
    ÑĢ
    1.25
    Ñģ
    1.17
    н
    1.17
    Ñ
    1.14
    ÑĤ
    1.11
    е
    1.06
    и
    0.99
    о
    0.97
     Ð
    0.96
    Ì
    0.87
    Activations Density 0.006%

    No Known Activations