© 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. 7445
    Prev
    Next
    INDEX
    Explanations

    instances of the word "happen" or forms of it, in conjunction with describing the occurrence of events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "happen to be."

    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
    bush
    -0.63
     Basics
    -0.60
    ebus
    -0.59
    ocker
    -0.57
     interpretation
    -0.55
     Base
    -0.55
     IPM
    -0.55
     submission
    -0.55
     Illusion
    -0.54
     Labs
    -0.53
    POSITIVE LOGITS
     upon
    0.81
    upon
    0.78
    rils
    0.76
    ALLY
    0.76
    ogn
    0.74
     to
    0.74
    uate
    0.73
    strate
    0.72
    llor
    0.71
    eor
    0.71
    Activations Density 0.047%

    No Known Activations