© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or situations that hinge on specific events or 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
    MpServer
    -0.78
    quartered
    -0.73
    76561
    -0.72
    angering
    -0.71
    interstitial
    -0.70
    ,,,,,,,,
    -0.68
    actionDate
    -0.68
    marked
    -0.65
     sqor
    -0.65
     Concern
    -0.64
    POSITIVE LOGITS
     decides
    1.40
     succeeds
    1.37
     develops
    1.33
     emerges
    1.27
     gets
    1.25
     survives
    1.24
     recovers
    1.23
     achieves
    1.23
     becomes
    1.22
     completes
    1.22
    Activations Density 0.336%

    No Known Activations