© 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. 7-RES-JB
    11. 24038
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or corporate documents and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political activities and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.75
     Cassidy
    -0.70
     Frie
    -0.69
     Krug
    -0.67
     Bravo
    -0.63
     Jagu
    -0.62
     vets
    -0.61
     Tough
    -0.61
     Nieto
    -0.61
     Keystone
    -0.61
    POSITIVE LOGITS
     persons
    0.88
     specified
    0.86
     hereby
    0.86
     Persons
    0.80
    /(
    0.77
     embodiments
    0.75
     foregoing
    0.75
     shall
    0.75
    :(
    0.72
     lawful
    0.71
    Activations Density 1.100%

    No Known Activations