© 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. 10-RES-JB
    11. 13920
    Prev
    Next
    INDEX
    Explanations

    phrases with "off the" followed by descriptions or actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "off the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.71
    mx
    -0.71
    Bi
    -0.70
    RIC
    -0.68
    CVE
    -0.66
    ymm
    -0.65
    parts
    -0.65
    partial
    -0.64
    lessness
    -0.64
    cific
    -0.64
    POSITIVE LOGITS
     beaten
    1.06
     coast
    1.00
     rails
    0.98
     leash
    0.98
     cliff
    0.98
     shelves
    0.97
     cuff
    0.95
     hinges
    0.94
     ledge
    0.94
     coasts
    0.91
    Activations Density 0.044%

    No Known Activations