© 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. 1-RES-JB
    11. 21200
    Prev
    Next
    INDEX
    Explanations

    words related to religious figures and organizations associated with faith

    oai_token-act-pair · gpt-3.5-turbo

    references to apostolic themes and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.82
    INTON
    -0.81
    UTION
    -0.80
    isher
    -0.75
    IVER
    -0.75
    ichick
    -0.74
    ball
    -0.72
     Brach
    -0.69
    boarding
    -0.69
    ibur
    -0.68
    POSITIVE LOGITS
     apost
    1.25
    rophe
    1.16
    olic
    0.96
    asy
    0.96
    ocry
    0.94
    olate
    0.88
     laure
    0.87
     Apost
    0.84
    algia
    0.84
    athy
    0.84
    Activations Density 0.014%

    No Known Activations