INDEX

Explanations

references to people, timestamps, and social media interactions or updates

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

 wireType

-0.57

 ddelweddau

-0.56

homonymie

-0.55

ſelves

-0.53

MemoryWarning

-0.52

 kasarigan

-0.51

ReusableCell

-0.51

WireFormatLite

-0.50

 JpaRepository

-0.50

請繼續往下閱讀

-0.49

POSITIVE LOGITS

 yesterday

1.02

Yesterday

0.87

 Yesterday

0.86

yesterday

0.84

 hours

0.79

 months

0.77

 вчера

0.75

 weeks

0.72

 gestern

0.72

昨天

0.71

Activations Density 0.029%

references to people, timestamps, and social media interactions or updates

No Comments

No Known Activations