INDEX

Explanations

conditional phrases indicating uncertainty or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 kasarigan

-0.89

DDG

-0.77

 jdbcTemplate

-0.66

談社

-0.66

jago

-0.65

 Martine

-0.65

ExceptionHandler

-0.65

XG

-0.64

ρους

-0.63

zade

-0.63

POSITIVE LOGITS

 whether

1.03

 WHETHER

0.92

 apakah

0.90

whether

0.86

 האם

0.82

 Whether

0.77

checkIf

0.71

Whether

0.69

SetBool

0.69

it

0.68

Activations Density 0.093%

conditional phrases indicating uncertainty or questions

No Comments

No Known Activations

conditional phrases indicating uncertainty or questions

No Comments

No Known Activations