INDEX

Explanations

mentions of self-awareness or personal experiences

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

here is / here's

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

ỏi

-0.45

ISHMENT

-0.44

 lobo

-0.43

 prefi

-0.43

agoza

-0.41

 maar

-0.40

blitz

-0.40

 outsource

-0.40

itakan

-0.40

 composition

-0.40

POSITIVE LOGITS

ValueStyle

0.71

IsMutable

0.69

 autorytatywna

0.68

ⓘ

0.67

原始内容存档

0.66

IGraphics

0.65

ContentAsync

0.64

hyrchwyd

0.63

OrBuilder

0.60

postIndex

0.60

Activations Density 0.033%

mentions of self-awareness or personal experiences

here is / here's

No Comments

No Known Activations