© 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. 0-RES-JB
    6. 5297
    Prev
    Next
    INDEX
    Explanations

    words related to the medical term "malignancy."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "ancy" indicating a state or condition

    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
     Rasm
    -0.67
     boxed
    -0.66
     ir
    -0.58
     closer
    -0.57
     Patriarch
    -0.57
     Rib
    -0.55
     parting
    -0.55
     Rod
    -0.54
     PBS
    -0.54
     proof
    -0.54
    POSITIVE LOGITS
    ancy
    4.80
    ancies
    3.30
    ants
    1.74
    antly
    1.65
    ance
    1.63
    ant
    1.62
    ancers
    1.62
    ANC
    1.60
    ances
    1.59
    ANCE
    1.55
    Activations Density 0.005%

    No Known Activations