INDEX

Explanations

references to the name "Margaret" and mentions of "cord."

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

出版年

-0.82

 Morty

-0.79

 Chichester

-0.74

selaer

-0.73

 HashSet

-0.72

 Industri

-0.72

Bav

-0.71

pin

-0.71

 Rocca

-0.71

hy

-0.71

POSITIVE LOGITS

ADA

0.77

fname

0.77

 cord

0.71

Evans

0.70

 fname

0.70

ADA

0.70

Ada

0.68

 Sada

0.68

 Evans

0.67

ada

0.67

Activations Density 0.037%

references to the name "Margaret" and mentions of "cord."

No Comments

No Known Activations