© 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 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. 9-RES-JB
    11. 14749
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific organizations, locations, or projects

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various fields or organizations

    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
     composition
    -0.72
     compositions
    -0.69
     embodiments
    -0.69
     composing
    -0.65
     muzzle
    -0.65
     biases
    -0.65
     tox
    -0.64
     nausea
    -0.64
    hesda
    -0.64
     metic
    -0.63
    POSITIVE LOGITS
     Association
    1.16
     Consortium
    1.12
     Agency
    1.05
     Cooperative
    1.01
     Authority
    1.00
     Service
    0.96
     Alliance
    0.94
     Network
    0.94
     Society
    0.93
     Lines
    0.93
    Activations Density 0.292%

    No Known Activations