© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 23597
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the name or term "Rubenstein"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Rubik" and its variations within the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricanes
    -0.74
    EXT
    -0.68
    aturally
    -0.65
     Span
    -0.63
     HERO
    -0.62
    ramer
    -0.62
     Titanic
    -0.61
     LIVE
    -0.61
     Modes
    -0.60
     CLASS
    -0.59
    POSITIVE LOGITS
    bish
    1.34
    bing
    1.32
    bery
    1.23
    bers
    1.15
    instein
    1.14
    idium
    1.09
     elbows
    1.08
    bles
    1.06
    rics
    1.01
    bed
    0.99
    Activations Density 0.030%

    No Known Activations