INDEX

Explanations

phrases that indicate actions or descriptions involving height or elevation

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

Preceding Roman numerals or numbers

np_acts-logits-general · gemini-2.0-flash

felt was

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 незавершена

-1.08

 صوتيه

-1.04

Datuak

-1.04

errHandler

-0.96

AndEndTag

-0.91

IsMutable

-0.91

 كومونز

-0.89

 للمعارف

-0.89

 فريبيس

-0.84

الإنجليزية

-0.84

POSITIVE LOGITS

was

0.69

 suddenly

0.61

his

0.60

he

0.59

 went

0.56

her

0.55

him

0.55

He

0.55

He

0.54

 immediately

0.54

Activations Density 1.255%

phrases that indicate actions or descriptions involving height or elevation

Preceding Roman numerals or numbers

felt was

No Comments

No Known Activations