INDEX

Explanations

instances of questions and their formatting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AntiForgeryToken

-0.62

neſs

-0.61

ſt

-0.60

دانشنامهٔ

-0.58

Спољашње

-0.57

 itſelf

-0.57

 Chriſt

-0.56

leſs

-0.56

IndentedString

-0.55

 STRA

-0.54

POSITIVE LOGITS

3.39

3.10

2.17

1.73

Ｑ

1.69

Qs

1.64

𝑄

1.25

Qn

1.23

ｑ

1.18

iQ

1.16

Activations Density 0.101%

instances of questions and their formatting

No Comments

No Known Activations