© 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. 10-RES-JB
    11. 8459
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual phrases and references

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Okay
    -0.88
     Heck
    -0.87
    Nick
    -0.87
    Hey
    -0.86
    Kids
    -0.83
    Wow
    -0.82
    Ops
    -0.80
     Plus
    -0.78
    Doug
    -0.77
    Josh
    -0.77
    POSITIVE LOGITS
     scarcely
    1.27
     hath
    1.26
     endeavour
    1.26
     tremb
    1.25
     shall
    1.23
     dw
    1.21
     consec
    1.18
     endeav
    1.17
     ought
    1.16
     confess
    1.15
    Activations Density 0.323%

    No Known Activations