INDEX

Explanations

dialogues or quotations in conversations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Houſe

-0.66

 Catho

-0.65

 catho

-0.63

principalTable

-0.63

 itſelf

-0.63

 المعيارى

-0.62

CloseOperation

-0.62

 myſelf

-0.61

 pleaſure

-0.60

 rospy

-0.59

POSITIVE LOGITS

webElement

0.65

WebElementEntity

0.57

 consultato

0.49

lleri

0.48

GeneratedValue

0.46

 ModelExpression

0.46

ianum

0.45

rawDesc

0.43

NewReader

0.42

 úgy

0.41

Activations Density 0.109%

dialogues or quotations in conversations

No Known Activations