© 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. 0-RES-JB
    11. 5311
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to "Mongo" or words containing "ongo"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and terms related to technology or biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obj
    -0.71
     Bian
    -0.65
     femin
    -0.65
    Jud
    -0.64
     Krist
    -0.64
     Jud
    -0.64
     Duel
    -0.63
     WRITE
    -0.63
     nudity
    -0.63
    Words
    -0.62
    POSITIVE LOGITS
    ongo
    3.02
    oglu
    2.77
    akin
    2.52
    ère
    1.08
    AKING
    1.01
    uj
    0.94
     awa
    0.87
    orsi
    0.87
    vas
    0.87
    achus
    0.87
    Activations Density 0.033%

    No Known Activations