INDEX

Explanations

terms and concepts associated with reversing or transformations in processes

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

"reverse" or its variations

np_acts-logits-general · gemini-2.0-flash

reverse and reversed

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ellemző

-0.44

ณา

-0.44

 تضيفلها

-0.43

amanan

-0.40

 godine

-0.40

RTCF

-0.40

为止

-0.39

IAA

-0.39

 mógł

-0.38

Gatt

-0.38

POSITIVE LOGITS

 reverse

2.16

 reversed

1.97

 Reverse

1.92

reverse

1.88

Reverse

1.83

 reverses

1.68

 reversing

1.66

reversed

1.64

 reversal

1.59

 inverse

1.52

Activations Density 0.473%

terms and concepts associated with reversing or transformations in processes

"reverse" or its variations

reverse and reversed

No Comments

No Known Activations