© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    6. 12984
    Prev
    Next
    INDEX
    Explanations

    mentions of clergy members or individuals associated with the clergy in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mention of clergy and associated themes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lima
    -0.81
     Kamp
    -0.78
     Tup
    -0.77
     Hatt
    -0.75
     Yamato
    -0.71
     Paulo
    -0.71
     Gat
    -0.70
     Ud
    -0.69
     Garg
    -0.69
     Gab
    -0.69
    POSITIVE LOGITS
     clergy
    1.00
    mares
    1.00
    casts
    0.84
    inav
    0.78
    icter
    0.77
    mare
    0.76
    sembly
    0.76
    EStreamFrame
    0.76
    women
    0.76
    NetMessage
    0.75
    Activations Density 0.026%

    No Known Activations