© 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. 666
    Prev
    Next
    INDEX
    Explanations

    mentions of atheism or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to atheism and related concepts

    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
     Zub
    -0.75
    FORMATION
    -0.70
    DERR
    -0.69
     DOE
    -0.68
     Mandela
    -0.64
    ENDED
    -0.63
    âĺħâĺħ
    -0.63
     Lemon
    -0.63
    uggest
    -0.62
     Westbrook
    -0.61
    POSITIVE LOGITS
    neum
    1.15
    rency
    0.93
     Athe
    0.92
    azi
    0.88
    ist
    0.86
    lington
    0.86
    nect
    0.85
    ists
    0.84
    ĪĴ
    0.83
    istical
    0.83
    Activations Density 0.010%

    No Known Activations