INDEX

Explanations

the word "a" 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 @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Попис

-0.57

èbre

-0.53

-0.51

HasAnnotation

-0.51

 כמה

-0.50

 دیکھیے

-0.49

 Theſe

-0.48

lepaskan

-0.46

basicConfig

-0.45

𝟹

-0.45

POSITIVE LOGITS

lot

2.06

Lot

1.27

LOT

1.26

Lot

1.22

ton

1.14

lot

1.12

 lots

1.02

 heck

0.98

LOT

0.97

 hell

0.97

Activations Density 0.183%

the word "a" in various contexts

No Comments

No Known Activations