INDEX

Explanations

phrases that reference spatial relationships or locations

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

"in" followed by a preposition or article

np_acts-logits-general · gemini-2.0-flash

affect in

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

migrationBuilder

-0.80

TagHelper

-0.67

 ExecuteAsync

-0.67

 ویکی‌پدیای

-0.65

RenderAtEndOf

-0.64

Portály

-0.63

 bezeichneter

-0.63

gonic

-0.61

 purpoſe

-0.60

AntiForgeryToken

-0.59

POSITIVE LOGITS

 front

0.64

LookAnd

0.58

 scolas

0.51

 desperation

0.48

front

0.48

 būt

0.44

 charge

0.44

 AudioClip

0.44

 Himo

0.44

charge

0.43

Activations Density 0.097%

phrases that reference spatial relationships or locations

"in" followed by a preposition or article

affect in

No Comments

No Known Activations