INDEX

Explanations

names of prominent individuals or characters

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

personal names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 transfieras

-0.53

 Савезне

-0.38

 joint

-0.36

 existing

-0.35

hasiswa

-0.34

 jointly

-0.33

rijfs

-0.32

 JOINT

-0.32

XmlAccessType

-0.32

ronpa

-0.32

POSITIVE LOGITS

UrlResolution

0.53

somebody

0.51

uncle

0.51

Somebody

0.49

adoc

0.48

MeasureSpec

0.47

 ویکی‌آمباردا

0.47

Klem

0.47

 يتيمه

0.47

 hydrochloride

0.46

Activations Density 0.021%

names of prominent individuals or characters

personal names

No Comments

No Known Activations