© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12672
    Prev
    Next
    INDEX
    Explanations

    phrases related to sinking or entrenching deeply into something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of 'sinking'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ³
    -0.71
    ============
    -0.70
    à¦
    -0.69
     SX
    -0.68
    kson
    -0.62
     calendars
    -0.61
    BOOK
    -0.61
     Sharif
    -0.60
    OGR
    -0.59
    RFC
    -0.59
    POSITIVE LOGITS
    hole
    1.04
    holes
    0.93
     sunk
    0.90
    minist
    0.87
    ucer
    0.85
     sink
    0.82
     overboard
    0.82
     sinking
    0.81
     deeper
    0.80
    ding
    0.80
    Activations Density 0.030%

    No Known Activations