© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20602
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    tentative phrases expressing uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.73
    enthal
    -0.66
    breakers
    -0.60
     cardinal
    -0.60
    XM
    -0.59
     Bird
    -0.58
    Rat
    -0.57
    é¾įå¥ij士
    -0.57
    âĺħ
    -0.56
    jri
    -0.55
    POSITIVE LOGITS
     wonder
    1.24
     notice
    1.17
     wanna
    1.14
     want
    1.13
     wondering
    1.06
     remember
    1.01
     ask
    1.00
     disagree
    0.98
     wish
    0.98
     wondered
    0.97
    Activations Density 0.068%

    No Known Activations