INDEX

Explanations

references to prestigious institutions or entities

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

Adjectives indicating high quality or ranking

np_acts-logits-general · gemini-2.0-flash

leading top foremost

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

RenderAtEndOf

-0.53

 StringTokenizer

-0.51

OrWhiteSpace

-0.51

AndEndTag

-0.50

ècie

-0.50

apnews

-0.49

Népesség

-0.49

HasBeenSet

-0.49

ModelAdmin

-0.48

ThroughAttribute

-0.48

POSITIVE LOGITS

 leading

1.45

 renowned

1.23

leading

1.20

top

1.13

Leading

1.12

eminent

1.12

 Leading

1.11

 füh

1.06

 eminent

1.03

 prominent

1.02

Activations Density 0.211%

references to prestigious institutions or entities

Adjectives indicating high quality or ranking

leading top foremost

No Comments

No Known Activations