INDEX

Explanations

statements about the presence or significance of certain conditions or criteria

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

Adjectives after the word "is" or another form of "be"

np_acts-logits-general · gemini-2.0-flash

states being described

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 poffe

-0.66

fromnode

-0.55

 esetén

-0.55

 חיצוניים

-0.54

 Réalisation

-0.53

 perfons

-0.52

 Gleichzeitig

-0.52

cheibe

-0.51

arsal

-0.51

новниш

-0.51

POSITIVE LOGITS

 varied

0.90

 similar

0.80

 unchanged

0.76

 diverse

0.74

 changed

0.74

 quite

0.68

 identical

0.67

 impeccable

0.66

similar

0.65

 quello

0.65

Activations Density 0.886%

statements about the presence or significance of certain conditions or criteria

Adjectives after the word "is" or another form of "be"

states being described

No Comments

No Known Activations