© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 9641
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "feta"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of fetuses and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.71
     Nationwide
    -0.68
     Galile
    -0.68
    FUL
    -0.67
    arta
    -0.67
    Phil
    -0.67
    è£ħ
    -0.66
    RAFT
    -0.65
     Diversity
    -0.64
    soType
    -0.64
    POSITIVE LOGITS
    fet
    1.10
     fet
    1.09
    ches
    1.08
    tered
    1.07
    ched
    1.05
    tering
    1.00
    ters
    0.95
    imes
    0.95
    ted
    0.92
    icular
    0.89
    Activations Density 0.011%

    No Known Activations