INDEX

Explanations

occurrences of the preposition "in"

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

"In" followed by a noun

np_acts-logits-general · gemini-2.0-flash

in [manner/state/sequence]

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

évaluateur

-0.75

 intermédiaire

-0.68

WebElementEntity

-0.67

 "..\..\

-0.66

:✨

-0.63

webElementGuid

-0.62

HasForeignKey

-0.61

 hinaus

-0.59

AnimationsModule

-0.59

WriteTagHelper

-0.57

POSITIVE LOGITS

 stages

0.85

 batches

0.82

 bulk

0.69

stages

0.65

 Stages

0.63

 increments

0.63

 multiples

0.63

 triplicate

0.63

 formats

0.62

Stages

0.62

Activations Density 0.413%

occurrences of the preposition "in"

"In" followed by a noun

in [manner/state/sequence]

No Comments

No Known Activations