© 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. 10-RES-JB
    11. 10634
    Prev
    Next
    INDEX
    Explanations

    uncertainty or speculation about potential future outcomes based on current events or actions

    oai_token-act-pair · gpt-3.5-turbo

    conditional and hypothetical phrases about possibilities and outcomes

    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
    onz
    -0.69
     accepting
    -0.65
     citing
    -0.61
    iard
    -0.60
    lication
    -0.57
     waging
    -0.56
     rel
    -0.56
     Maid
    -0.56
    vati
    -0.55
    pard
    -0.54
    POSITIVE LOGITS
     happen
    1.56
     happened
    1.24
     transpired
    1.20
     happens
    1.13
     happ
    1.08
     occur
    1.06
     motivate
    1.02
     Happ
    1.00
     constitute
    0.90
     await
    0.84
    Activations Density 0.095%

    No Known Activations