INDEX

Explanations

phrases that indicate causation or conditions affecting outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 initComponents

-0.77

abestanden

-0.76

Efq

-0.70

 المعيارى

-0.68

 faſt

-0.64

 Monfieur

-0.63

StoryboardSegue

-0.62

 OFDb

-0.61

 fubject

-0.59

 OMITBAD

-0.59

POSITIVE LOGITS

 because

0.83

的原因

0.82

 sababu

0.76

 perché

0.74

 reason

0.72

 partly

0.70

due

0.69

 perquè

0.68

 原因

0.67

原因

0.67

Activations Density 0.387%

phrases that indicate causation or conditions affecting outcomes

No Comments

No Known Activations