INDEX

Explanations

descriptive and contrasting qualities of characters

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

preceding "-ard" or "-ent" suffixes

np_acts-logits-general · gemini-2.0-flash

character descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

astify

-0.87

ChromeDriver

-0.70

 charité

-0.68

 dévelo

-0.67

 gouver

-0.67

HandlerContext

-0.67

AndEndTag

-0.67

 conduite

-0.65

MLLoader

-0.65

جستارهای

-0.65

POSITIVE LOGITS

lon

0.65

gad

0.61

 smooth

0.57

eg

0.54

 wheeler

0.54

 raff

0.52

wheeler

0.52

 roue

0.51

 wast

0.51

 itiner

0.51

Activations Density 0.246%

descriptive and contrasting qualities of characters

preceding "-ard" or "-ent" suffixes

character descriptors

No Comments

No Known Activations