INDEX

Explanations

concepts related to trust, respect, and judgment in various contexts

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

following verbs expressing opinions/judgments

np_acts-logits-general · gemini-2.0-flash

complaint accusation trust"},

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

Not in Any Lists

No Comments

Negative Logits

usehen

-0.53

úrese

-0.51

θυ

-0.49

dymyr

-0.46

asiun

-0.45

nữ

-0.42

StandardCharsets

-0.42

 Under

-0.41

تأ

-0.41

gura

-0.41

POSITIVE LOGITS

 Factbook

0.60

 AssemblyProduct

0.60

 Exacts

0.60

 дописавши

0.60

 terhadap

0.57

 asupra

0.57

ngrx

0.57

 saites

0.57

SharedDtor

0.57

 Lightboxes

0.57

Activations Density 0.451%

concepts related to trust, respect, and judgment in various contexts

following verbs expressing opinions/judgments

complaint accusation trust"},

No Comments

No Known Activations