© 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. 6-RES-JB
    11. 13639
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to the BM (body mass) terminology and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivity
    -0.77
    sis
    -0.74
    lihood
    -0.73
    iency
    -0.71
    paralle
    -0.69
    breaks
    -0.68
    iott
    -0.68
    lich
    -0.65
    renheit
    -0.65
    enced
    -0.64
    POSITIVE LOGITS
    ODY
    0.81
    ailability
    0.78
    ohydrate
    0.75
    è¦ļéĨĴ
    0.72
     Cum
    0.70
    azo
    0.69
    ucket
    0.69
    ohyd
    0.69
    unk
    0.68
    ooth
    0.68
    Activations Density 0.042%

    No Known Activations