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

    Neuronpedia

    Jacobian LensNEW
    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. 14863
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or speculation

    oai_token-act-pair · gpt-3.5-turbo

    conditional and future-oriented modal verbs that express likelihood or possibility

    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
    soDeliveryDate
    -0.77
     Sandwich
    -0.65
     Palest
    -0.63
    Room
    -0.62
    AAA
    -0.61
    CLASSIFIED
    -0.60
     Became
    -0.59
    HD
    -0.59
    Reloaded
    -0.59
     Mata
    -0.58
    POSITIVE LOGITS
     attest
    1.38
     scoff
    1.19
     disapprove
    1.18
     agree
    1.17
     gladly
    1.17
     cringe
    1.15
     balk
    1.14
     disagree
    1.14
     argue
    1.12
     rejoice
    1.09
    Activations Density 0.158%

    No Known Activations