INDEX

Explanations

conversational phrases that indicate personal experiences and social interactions

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

before modifying adjectives

np_acts-logits-general · gemini-2.0-flash

mutant receptors, competitive features, two molecules

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

makeConstraints

-0.82

__*/

-0.78

सन्दर्भ

-0.77

ⓧ

-0.72

 vermelhas

-0.72

 contextLoads

-0.70

 holotype

-0.70

 Paglinawan

-0.69

تقاوى

-0.69

CGRectMake

-0.68

POSITIVE LOGITS

 kasarigan

0.69

чности

0.54

dding

0.54

ting

0.53

 وسلم

0.52

htë

0.52

lichkeit

0.52

lles

0.51

su

0.50

delà

0.50

Activations Density 1.794%

conversational phrases that indicate personal experiences and social interactions

before modifying adjectives

mutant receptors, competitive features, two molecules

No Comments

No Known Activations