© 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. 12048
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the drug lord Pablo Escobar

    oai_token-act-pair · gpt-3.5-turbo
    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
    fuck
    -0.69
     partName
    -0.66
     é
    -0.65
     ABS
    -0.65
    ãĥĩãĤ£
    -0.63
     Taiwanese
    -0.62
     Jenner
    -0.62
    åĤ
    -0.62
     belt
    -0.61
     Dynamics
    -0.60
    POSITIVE LOGITS
    apist
    1.29
    ribed
    1.26
    apes
    1.15
    aped
    1.14
    aping
    1.13
    orts
    1.12
    ribing
    1.08
    obar
    1.06
    apers
    1.04
    udo
    1.01
    Activations Density 0.028%

    No Known Activations