© 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. 2-RES-JB
    6. 23671
    Prev
    Next
    INDEX
    Explanations

    the word "Karp" with different numbers indicating varying degrees of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity with the name "Karp."

    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
     Democr
    -0.77
     Coke
    -0.76
    FUL
    -0.67
     Bulls
    -0.64
     Buc
    -0.64
    20439
    -0.64
     Cavaliers
    -0.64
    ãĤ±
    -0.63
     ACTIONS
    -0.63
     CARE
    -0.62
    POSITIVE LOGITS
    olitics
    1.16
    etry
    1.08
    odcast
    1.02
    arp
    1.02
    ocalypse
    0.99
    adia
    0.99
    acing
    0.97
    isode
    0.94
    olicy
    0.93
    artisan
    0.91
    Activations Density 0.010%

    No Known Activations