© 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. 2-RES-JB
    11. 14710
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "feta"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fetuses and fetishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solution
    -0.68
     Dragonbound
    -0.68
    FUL
    -0.68
     Diversity
    -0.68
     Bravo
    -0.65
    arta
    -0.63
    soType
    -0.62
    é¾
    -0.62
     Sher
    -0.61
     Sahara
    -0.61
    POSITIVE LOGITS
     fet
    1.15
    fet
    1.13
    tered
    0.98
    ches
    0.97
    ched
    0.94
    imes
    0.94
    tering
    0.92
     Fet
    0.90
    mons
    0.87
    ters
    0.86
    Activations Density 0.008%

    No Known Activations