INDEX

Explanations

phrases related to trust, accountability, and legal or procedural issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.77

peteer

-0.50

tiness

-0.49

defn

-0.49

SOUNDBITE

-0.47

setToolTip

-0.47

resaid

-0.47

Története

-0.47

 NSCoder

-0.46

__(/*!

-0.46

POSITIVE LOGITS

 done

0.93

done

0.79

Doing

0.75

 DONE

0.75

 Done

0.70

 EconPapers

0.69

 ujednoznacz

0.68

doing

0.67

Done

0.66

 feito

0.65

Activations Density 0.032%

phrases related to trust, accountability, and legal or procedural issues

No Comments

No Known Activations