© 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. 0-RES-JB
    11. 13884
    Prev
    Next
    INDEX
    Explanations

    news headlines or titles with uppercase words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "JUST" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢIJ
    -0.91
     possession
    -0.70
     ÂŃ
    -0.66
     Tri
    -0.65
    ÂŃ
    -0.64
     basement
    -0.60
     nursery
    -0.59
     prone
    -0.59
     Queen
    -0.58
     Cent
    -0.58
    POSITIVE LOGITS
    JUST
    4.74
    SPONSORED
    1.31
     JUSTICE
    1.17
    CNN
    1.15
    Photos
    1.13
     JUST
    1.13
    just
    1.12
    CLOSE
    1.06
    Enlarge
    1.04
    RELATED
    1.04
    Activations Density 0.014%

    No Known Activations