INDEX

Explanations

the word "too" and its variations, indicating excessiveness or frequency

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

"too" and punctuation

np_acts-logits-general · gemini-2.0-flash

intensifier 'too'

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

 vaisselle

-0.79

ly

-0.73

Kend

-0.70

ști

-0.65

roves

-0.64

(\

-0.62

batik

-0.62

Kennedy

-0.60

 Chalmers

-0.60

了

-0.59

POSITIVE LOGITS

TOO

1.20

too

1.16

Too

1.15

TOO

1.15

too

1.12

Too

1.05

troppo

0.94

醐

0.86

 TOOL

0.81

 CreateTagHelper

0.78

Activations Density 0.040%

the word "too" and its variations, indicating excessiveness or frequency

"too" and punctuation

intensifier 'too'

No Comments

No Known Activations