INDEX

Explanations

articles (a, an, the) in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 незавершена

-1.20

 дописавши

-1.17

 '\\;'

-1.12



-1.06

OGND

-1.02

Personendaten

-1.01

BeginContext

-0.99

 Signalez

-0.97

Datuak

-0.97

 NSCoder

-0.97

POSITIVE LOGITS

0.80

 large

0.58

an

0.56

Go

0.56

the

0.56

0.53

 small

0.53

 central

0.51

Activations Density 0.249%

articles (a, an, the) in various contexts

No Comments

No Known Activations