© 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. 2-RES-JB
    11. 22557
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or events related to specific Baptist churches

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Baptist" in various contexts

    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
     IST
    -0.77
    pmwiki
    -0.74
    âĶĢâĶĢ
    -0.70
    obbies
    -0.68
    Drug
    -0.66
    utherford
    -0.66
    udic
    -0.65
     TYPE
    -0.65
    PF
    -0.65
    avez
    -0.64
    POSITIVE LOGITS
     Baptist
    1.27
     Bapt
    0.92
    eering
    0.90
    ©¶æ¥µ
    0.90
     missionaries
    0.86
    nect
    0.83
     evangel
    0.79
     tracts
    0.79
     pastor
    0.75
     bapt
    0.75
    Activations Density 0.005%

    No Known Activations