© 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. 5243
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "thing"

    oai_token-act-pair · gpt-3.5-turbo

    references to generalized or specific objects, often indicated by the word "thing."

    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
     profiles
    -0.75
     Rush
    -0.68
     sensitivity
    -0.65
     deficit
    -0.64
     Listen
    -0.64
     Def
    -0.59
     caps
    -0.58
     families
    -0.57
     screen
    -0.57
     estimates
    -0.57
    POSITIVE LOGITS
    thing
    5.02
    things
    2.12
    THING
    1.49
     Thing
    1.42
     thing
    1.28
    stuff
    1.22
    ths
    1.21
    something
    1.03
    thin
    1.01
    ther
    0.98
    Activations Density 0.009%

    No Known Activations