INDEX

Explanations

phrases indicating personal experiences and perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

setVerticalGroup

-0.86

 initComponents

-0.71

PreferredItem

-0.71

ंदीखरीदारी

-0.67

DockStyle

-0.67

 فريبيس

-0.64

Efq

-0.62

 onAnimation

-0.59

LookAnd

-0.59

 EconPapers

-0.59

POSITIVE LOGITS

 referring

2.09

 refer

1.94

 refers

1.83

refer

1.70

 mean

1.66

 meaning

1.57

 reference

1.56

 MEAN

1.44

 maksud

1.43

 Refer

1.42

Activations Density 0.352%

phrases indicating personal experiences and perspectives

No Comments

No Known Activations