INDEX

Explanations

terms related to "eye" and "eye contact."

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

"eye" or "eyes"

np_acts-logits-general · gemini-2.0-flash

eye, eyes, and related concepts

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

はじめに

-0.55

SPATH

-0.54

ly

-0.52

CONSIDER

-0.51

-0.50

 дописавши

-0.50

 disponibilités

-0.49

mente

-0.49

łaszcza

-0.49

ⓧ

-0.49

POSITIVE LOGITS

eye

0.87

EYE

0.84

eyes

0.82

EYE

0.78

 eyes

0.78

Eyes

0.78

eye

0.78

Eye

0.78

 Eyes

0.77

 EYES

0.73

Activations Density 0.046%

terms related to "eye" and "eye contact."

"eye" or "eyes"

eye, eyes, and related concepts

No Comments

No Known Activations