INDEX

Explanations

comparative phrases and assertions related to evaluations and measurements

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

Prepositions, especially "to"

np_acts-logits-general · gemini-2.0-flash

round to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 Majefty

-0.52

RenderAtEndOf

-0.51

 lenker

-0.48

webElementXpaths

-0.48

 faſt

-0.47

tinyos

-0.45

цездатний

-0.45

 myſelf

-0.42

 ſta

-0.41

DoubleQuotes

-0.39

POSITIVE LOGITS

tothe

0.63

到

0.62

to

0.59

至

0.54

 extent

0.51

 degree

0.51

To

0.50

zum

0.49

To

0.48

 đến

0.47

Activations Density 0.308%

comparative phrases and assertions related to evaluations and measurements

Prepositions, especially "to"

round to

No Comments

No Known Activations