© 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. 18005
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual references

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and conjunctions that connect thoughts or ideas

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.88
    CNN
    -0.86
    DAQ
    -0.83
     takeaway
    -0.79
    Focus
    -0.79
    rored
    -0.77
    taboola
    -0.75
    ongo
    -0.73
    guy
    -0.73
    VICE
    -0.72
    POSITIVE LOGITS
     whence
    1.16
     viz
    1.15
     yea
    1.06
     thence
    1.04
     whereby
    1.03
     etc
    1.01
     qui
    0.99
     wherein
    0.98
     tho
    0.95
     whilst
    0.93
    Activations Density 0.387%

    No Known Activations