INDEX

Explanations

forms of the verb "have."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

parsedMessage

-0.83

SharedCtor

-0.74

ībā

-0.65

-0.64

MessageTagHelper

-0.62

PreferredItem

-0.62

собенно

-0.60

 katanya

-0.60

 Italijanski

-0.59

 الرياضيه

-0.58

POSITIVE LOGITS

 been

1.26

1.01

 gotten

0.99

 gone

0.98

an

0.89

 taken

0.81

had

0.81

been

0.79

 come

0.78

 begun

0.78

Activations Density 0.419%

forms of the verb "have."

No Comments

No Known Activations