© 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. 11-RES-JB
    11. 3475
    Prev
    Next
    INDEX
    Explanations

    legally-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    formal communication regarding decisions and consultations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     someday
    -0.79
    iannopoulos
    -0.73
     trendy
    -0.68
     ruining
    -0.67
     Die
    -0.67
     Mysterious
    -0.65
     afterlife
    -0.65
    evil
    -0.65
     ruin
    -0.64
     pricey
    -0.64
    POSITIVE LOGITS
     briefed
    1.04
     vetted
    1.00
     ourselves
    0.95
     unanimously
    0.94
     communicated
    0.92
     consultation
    0.91
     consultations
    0.88
     consulted
    0.86
     stakeholders
    0.85
     feedback
    0.85
    Activations Density 0.929%

    No Known Activations