INDEX

Explanations

suggestive phrases or expressions that indicate recommendations or choices

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

Recommendations and suggestions

np_acts-logits-general · gemini-2.0-flash

recommendations and suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ご了承ください

-0.66

่านั้น

-0.63

ご了承

-0.59

 giudi

-0.57

 nawr

-0.56

 enää

-0.56

 kuiten

-0.56

 основном

-0.55

RetentionPolicy

-0.55

 ujednoznacz

-0.54

POSITIVE LOGITS

 consider

1.60

 Consider

1.44

Consider

1.37

consider

1.33

try

1.30

CONSIDER

1.20

 CONSIDER

1.18

Try

1.15

Try

1.11

 considera

1.08

Activations Density 0.236%

suggestive phrases or expressions that indicate recommendations or choices

Recommendations and suggestions

recommendations and suggestions

No Comments

No Known Activations