INDEX

Explanations

HTML tag structures and formats

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

HTML paragraph tag

np_acts-logits-general · gemini-2.0-flash

closing html tags

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

Negative Logits

expandindo

-0.87

contentLoaded

-0.72

RenderAtEndOf

-0.71

Geplaatst

-0.61

bootstrapcdn

-0.57

ьаж

-0.56

kom

-0.56

 bombar

-0.53

__*/

-0.53

mybatisplus

-0.52

POSITIVE LOGITS

SequentialGroup

0.97

脚注の使い方

0.64

 rafts

0.63

VIAF

0.60

 sportivo

0.58

 pazi

0.58

 pail

0.57

 Infórmanos

0.57

állítás

0.56

Activations Density 0.038%

HTML tag structures and formats

HTML paragraph tag

closing html tags

No Known Activations