© 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. 2-RES-JB
    11. 23780
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and figures, such as biblical verses and names

    oai_token-act-pair · gpt-3.5-turbo

    references to religious texts and concepts

    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
     Trend
    -0.72
    hover
    -0.69
     joystick
    -0.69
     Wag
    -0.68
    icio
    -0.68
     Dragonbound
    -0.67
     Sporting
    -0.66
     actionGroup
    -0.65
     Fisheries
    -0.65
     Varg
    -0.64
    POSITIVE LOGITS
     Scripture
    1.24
     scripture
    1.14
     Apostle
    1.09
     Scriptures
    1.08
     Psal
    1.06
     theolog
    1.06
     Apostles
    1.03
     bapt
    1.01
    byter
    1.01
     Romans
    1.01
    Activations Density 0.345%

    No Known Activations