© 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. 23009
    Prev
    Next
    INDEX
    Explanations

    verbs in the past or conditional tense

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases involving the word "would."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    è¦ļéĨĴ
    -0.81
     Gad
    -0.73
    pires
    -0.68
    quickShipAvailable
    -0.68
     contrasted
    -0.66
    Materials
    -0.64
     entails
    -0.62
     underscores
    -0.62
     distinguishes
    -0.62
     aggregation
    -0.61
    POSITIVE LOGITS
    nt
    1.27
     NEVER
    1.16
    've
    1.10
     never
    1.08
    never
    1.06
     gladly
    0.98
     definitely
    0.98
     probably
    0.98
    probably
    0.97
     wanna
    0.95
    Activations Density 0.203%

    No Known Activations