© 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. 0-RES-JB
    11. 12290
    Prev
    Next
    INDEX
    Explanations

    phrases related to impending events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Soon"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equ
    -0.72
     except
    -0.64
     defined
    -0.63
     versus
    -0.62
     restraint
    -0.61
     excluding
    -0.61
     valid
    -0.60
     cent
    -0.59
     considered
    -0.58
     neg
    -0.57
    POSITIVE LOGITS
     Soon
    3.77
    Soon
    2.72
    soon
    2.18
     soon
    1.76
     Eventually
    1.72
    Eventually
    1.56
     Shortly
    1.53
     Slowly
    1.43
     Later
    1.41
     Suddenly
    1.38
    Activations Density 0.012%

    No Known Activations