© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15274
    Prev
    Next
    INDEX
    Explanations

    dates, locations, and names with titles

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to academic citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    raits
    -0.68
     docs
    -0.66
     WEEK
    -0.64
     veggies
    -0.63
     ::
    -0.61
    SHARE
    -0.59
     Dems
    -0.58
     VIDE
    -0.58
     PLAN
    -0.57
    htaking
    -0.57
    POSITIVE LOGITS
    .[
    2.72
    ,[
    2.72
    ".[
    2.64
    ).[
    2.52
    ."[
    2.28
    [
    2.21
    :[
    2.15
    )[
    2.06
    ][
    1.82
    "[
    1.72
    Activations Density 0.362%

    No Known Activations