© 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. 10-RES-JB
    6. 6317
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ma" followed by a name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ma" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AAP
    -0.67
    sed
    -0.67
    side
    -0.64
    tap
    -0.62
    lined
    -0.61
    ttes
    -0.61
     expanding
    -0.60
    deck
    -0.59
     hotter
    -0.57
     paved
    -0.57
    POSITIVE LOGITS
    ureen
    1.46
    estro
    1.44
    ples
    1.21
    arten
    1.15
    isel
    1.04
    ude
    1.04
    pler
    1.03
    xt
    1.00
    urer
    0.98
    iami
    0.98
    Activations Density 0.016%

    No Known Activations