© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2544
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating possession or relationship

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and their associated verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaz
    -0.76
     Barron
    -0.72
    ourgeois
    -0.70
    hatt
    -0.69
    geries
    -0.66
     Revolution
    -0.65
    yss
    -0.65
     Ukrain
    -0.63
    ategory
    -0.62
    inctions
    -0.61
    POSITIVE LOGITS
     deems
    0.97
     deemed
    0.94
     cherish
    0.89
     sorely
    0.86
     deem
    0.86
     hadn
    0.81
     dearly
    0.81
     cannot
    0.80
     couldn
    0.78
     knew
    0.78
    Activations Density 0.169%

    No Known Activations