© 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. 3-RES-JB
    11. 23655
    Prev
    Next
    INDEX
    Explanations

    religious or divine references

    oai_token-act-pair · gpt-3.5-turbo

    references to deities and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.90
    anwhile
    -0.84
    jri
    -0.78
    essional
    -0.77
    eport
    -0.76
    UGC
    -0.75
    Downloadha
    -0.74
     restrooms
    -0.70
    izont
    -0.70
     showc
    -0.70
    POSITIVE LOGITS
     Nebula
    0.89
     Beasts
    0.83
     Loki
    0.76
     Yamato
    0.75
     Almighty
    0.75
     Monstrous
    0.75
     Leia
    0.73
     Nemesis
    0.73
     reincarn
    0.73
     Apocalypse
    0.72
    Activations Density 0.714%

    No Known Activations