© 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. 11-RES-JB
    11. 2142
    Prev
    Next
    INDEX
    Explanations

    the word "is" followed by a description or statement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ares
    -0.76
    aired
    -0.68
    umbs
    -0.67
    è¦ļéĨĴ
    -0.62
    stocks
    -0.61
    enth
    -0.61
    iaries
    -0.60
    chairs
    -0.58
    olds
    -0.58
    eals
    -0.58
    POSITIVE LOGITS
     nothing
    1.20
     no
    1.11
     plenty
    1.06
     something
    1.04
     nowhere
    1.03
     ALWAYS
    1.00
     ample
    0.99
     always
    0.99
     absolutely
    0.98
     definitely
    0.97
    Activations Density 0.099%

    No Known Activations