© 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. 2-RES-JB
    11. 9899
    Prev
    Next
    INDEX
    Explanations

    references to a criminal organization named "Cartel."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Cartel."

    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
    FORMATION
    -0.85
    Downloadha
    -0.84
    IDENT
    -0.77
    ITED
    -0.73
    HUD
    -0.72
    LEASE
    -0.69
    idency
    -0.69
    BIP
    -0.66
     Bruins
    -0.65
    00200000
    -0.65
    POSITIVE LOGITS
    ilage
    1.18
    otle
    1.14
    cart
    1.10
     Cart
    1.07
    Cart
    1.06
    esian
    1.05
    wright
    0.96
    oons
    0.95
    artisan
    0.91
    ridges
    0.91
    Activations Density 0.006%

    No Known Activations