© 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. 18199
    Prev
    Next
    INDEX
    Explanations

    verbs describing actions that challenge or oppose something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "def" and its various forms, indicating a focus on definitions or related terminology

    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
     Norn
    -0.82
    ippi
    -0.81
    wine
    -0.81
    ciating
    -0.73
    etus
    -0.68
     Hare
    -0.68
     Ore
    -0.67
    hare
    -0.66
    ingle
    -0.66
    early
    -0.66
    POSITIVE LOGITS
     def
    3.79
    def
    2.12
     Def
    1.54
    Def
    1.38
    DEF
    1.31
     DEF
    1.30
     defect
    1.20
     deflect
    1.17
     diss
    1.05
     deflation
    1.00
    Activations Density 0.013%

    No Known Activations