© 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. 7-RES-JB
    11. 7836
    Prev
    Next
    INDEX
    Explanations

    mentions of religious terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to religion and its impact on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •911

    No Comments

    Negative Logits
    kus
    -0.76
     Lans
    -0.74
    hap
    -0.70
     Rober
    -0.67
    ription
    -0.67
    berry
    -0.66
     Straw
    -0.65
    asper
    -0.64
     Yon
    -0.64
    berries
    -0.63
    POSITIVE LOGITS
    ophobia
    0.96
    ophobic
    0.90
    fulness
    0.88
    istical
    0.84
    igion
    0.82
     tenets
    0.81
    ically
    0.81
    hood
    0.79
    ical
    0.79
    etics
    0.78
    Activations Density 0.030%

    No Known Activations