INDEX

Explanations

instances of the prefix "un-" indicating negation or reversal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 MainAxisSize

-0.97

 StatelessWidget

-0.97

 StatefulWidget

-0.95

 Phry

-0.89

 protoimpl

-0.88

styleType

-0.87

yargs

-0.86

 SAGE

-0.86

 wireType

-0.82

 createState

-0.81

POSITIVE LOGITS

UN

1.31

UN

1.25

Un

1.22

un

1.15

Bun

1.02

Un

1.02

un

1.00

bun

0.94

Bun

0.92

Tun

0.91

Activations Density 0.239%

instances of the prefix "un-" indicating negation or reversal

No Comments

No Known Activations