INDEX

Explanations

references to the word "other."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tacitus

-0.80

 Francine

-0.78

 Miki

-0.73

 liturgy

-0.72

bankan

-0.72

झे

-0.67

 encephalitis

-0.67

 vectorielles

-0.66

Sagittarius

-0.66

 pancreatitis

-0.66

POSITIVE LOGITS

worldly

1.21

 other

1.14

 OTHER

1.04

autres

1.03

 Other

1.03

Other

1.02

other

0.94

OTHER

0.90

 kinds

0.86

 altra

0.84

Activations Density 0.125%

references to the word "other."

No Comments

No Known Activations