INDEX

Explanations

frequency and quantity of attributes or measurements mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.47

Bo

-0.46

No

-0.45

-0.41

↵↵

-0.41

Yii

-0.40

-0.39

POSITIVE LOGITS

 leaſt

1.25

 propOrder

1.09

NUMX

1.06

 Theſe

0.98

выше

0.97

Efq

0.95

 CreateTagHelper

0.95

 torno

0.93

ValueStyle

0.93

 fewest

0.92

Activations Density 0.255%

frequency and quantity of attributes or measurements mentioned in the text

No Comments

No Known Activations