INDEX

Explanations

articles and common verbs indicating actions or roles

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

Positive adjectives after indefinite articles

np_acts-logits-general · gemini-2.0-flash

positive evaluations after articles

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

Général

-0.66

يكب

-0.63

 rarest

-0.58

 darkest

-0.56

 coldness

-0.56

artem

-0.56

เร็

-0.54

neſs

-0.52

 blackness

-0.51

 tropics

-0.51

POSITIVE LOGITS

énario

0.66

andReturn

0.63

IntoConstraints

0.62

rungsseite

0.58

 promising

0.57

 fine

0.56

 excellent

0.56

 significa

0.56

agrama

0.56

 valid

0.55

Activations Density 0.493%

articles and common verbs indicating actions or roles

Positive adjectives after indefinite articles

positive evaluations after articles

No Comments

No Known Activations