© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10071
    Prev
    Next
    INDEX
    Explanations

    future tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    conditional or future tense verbs indicating uncertainty or speculation

    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
    Cra
    -0.64
    checked
    -0.62
     Medline
    -0.61
     Yep
    -0.61
    Yep
    -0.60
     Nope
    -0.58
    requisite
    -0.58
    quickShipAvailable
    -0.57
    cedented
    -0.57
     Coff
    -0.56
    POSITIVE LOGITS
     respond
    1.24
     proceed
    1.20
     react
    1.17
     fare
    1.15
     reconcile
    1.11
     handle
    1.08
     navigate
    1.07
     cope
    1.07
     behave
    1.05
     interact
    1.02
    Activations Density 0.116%

    No Known Activations