INDEX

Explanations

phrases indicating contradiction or opposing viewpoints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

+#+

-0.51

المشاركات

-0.46

numerusform

-0.45

 Himo

-0.42

ってもら

-0.42

ять

-0.42

 Awak

-0.39

šiť

-0.39

 OFDb

-0.39

 turun

-0.39

POSITIVE LOGITS

 myth

0.74

 rumors

0.71

 myths

0.70

 feared

0.68

 initComponents

0.68

 misleading

0.67

Rumors

0.65

 claims

0.65

 rumours

0.64

 fears

0.64

Activations Density 0.491%

phrases indicating contradiction or opposing viewpoints

No Comments

No Known Activations