© 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. 9528
    Prev
    Next
    INDEX
    Explanations

    phrases related to preserving something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "preserve" and its variations

    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
    ento
    -0.67
    kers
    -0.66
    pled
    -0.65
    bid
    -0.64
    chy
    -0.63
    hour
    -0.63
    pheus
    -0.63
    quarters
    -0.61
    ker
    -0.61
    gs
    -0.60
    POSITIVE LOGITS
     preserves
    1.20
     preservation
    1.17
     preserving
    1.10
     preserve
    1.05
    conservancy
    0.95
     preserved
    0.93
     conserv
    0.92
     intact
    0.86
     conserve
    0.83
    urally
    0.81
    Activations Density 0.013%

    No Known Activations