INDEX

Explanations

expressions of knowledge and understanding related to personal beliefs and experiences

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

"I know"

np_acts-logits-general · gemini-2.0-flash

know this/it/that

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.80

 ModelExpression

-0.75

homonymie

-0.67

gdx

-0.64

 EconPapers

-0.61

 Reverso

-0.60

instead

-0.59

 Instead

-0.57

yargs

-0.55

таратура

-0.55

POSITIVE LOGITS

 betul

0.71

 samfun

0.60

BeginContext

0.60

 doskon

0.59

 perfectamente

0.57

 firsthand

0.56

 intellectually

0.56

 sekali

0.56

 banget

0.55

 aimé

0.54

Activations Density 0.097%

expressions of knowledge and understanding related to personal beliefs and experiences

"I know"

know this/it/that

No Comments

No Known Activations