INDEX

Explanations

instances of the word "in."

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

"in"

np_acts-logits-general · gemini-2.0-flash

in

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pleaſure

-0.81

 purpoſe

-0.79

 ſta

-0.74

 myſelf

-0.70

 itſelf

-0.69

neſs

-0.66

 ſche

-0.66

 faſt

-0.66

 raiſ

-0.65

 ſtand

-0.65

POSITIVE LOGITS

in

1.48

In

1.09

In

1.02

in

0.93

IN

0.91

 في

0.82

ใน

0.82

 isIn

0.78

в

0.77

isIn

0.75

Activations Density 1.109%

instances of the word "in."

"in"

in

No Comments

No Known Activations