INDEX

Explanations

instances of the word "this" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.64

-0.48

•

-0.47

</strong>

-0.46

↵

-0.45

</h2>

-0.43

novation

-0.43

 esetén

-0.42

itum

-0.42

POSITIVE LOGITS

 متعلقه

1.23

دانشنامهٔ

1.23

rungsseite

1.14

 المعيارى

1.12

 propOrder

1.11

 kasarigan

1.08

脚注の使い方

1.06

 صوتيه

1.05

 tartalomajánló

1.02

 surla

1.00

Activations Density 0.298%

instances of the word "this" in the text

No Comments

No Known Activations