© 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
    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. 7556
    Prev
    Next
    INDEX
    Explanations

    Biblical references and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to religious or scriptural citations

    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
    ortunately
    -0.68
     stamp
    -0.68
     tack
    -0.66
     behavi
    -0.66
     popcorn
    -0.66
     clos
    -0.65
     consolid
    -0.65
     tradem
    -0.64
     pudding
    -0.62
     plush
    -0.62
    POSITIVE LOGITS
    1
    1.37
    6
    1.29
    5
    1.28
    8
    1.27
    7
    1.27
    4
    1.26
    3
    1.26
    9
    1.26
    31
    1.24
    11
    1.23
    Activations Density 0.022%

    No Known Activations