INDEX

Explanations

elements related to authority and control in legal or organizational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.79

 insuffisamment

-0.59

 Wikimedijinoj

-0.58

SizeF

-0.56

WriteBarrier

-0.54

misu

-0.50

AutoresizingMask

-0.50

atorics

-0.46

ETA

-0.45

quartered

-0.45

POSITIVE LOGITS

怎么可能

0.66

 unlikely

0.64

would

0.61

arbeid

0.60

 would

0.57

unlikely

0.56

とは思

0.56

 būtų

0.55

ChildIndex

0.55

bootstrapcdn

0.53

Activations Density 0.358%

elements related to authority and control in legal or organizational contexts

No Comments

No Known Activations