© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 24010
    Prev
    Next
    INDEX
    Explanations

    references to specific religious terms related to apostasy and Protestantism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to apostasy and Protestantism

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

    No Comments

    Negative Logits
    veyard
    -0.76
    pty
    -0.75
    pees
    -0.74
    berman
    -0.74
    pee
    -0.72
    isite
    -0.70
    imens
    -0.69
    pless
    -0.69
    imoto
    -0.69
    nesota
    -0.69
    POSITIVE LOGITS
    rophe
    0.93
    ritis
    0.89
    rop
    0.88
    oiler
    0.86
    edly
    0.86
    rom
    0.85
    lying
    0.83
    ortion
    0.83
    ly
    0.82
    ror
    0.82
    Activations Density 0.031%

    No Known Activations