INDEX

Explanations

instances of the word "decided"

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

"decided"

np_acts-logits-general · gemini-2.0-flash

deciding to do something

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

BagLayout

-0.63

idespread

-0.54

maru

-0.54

 Artemis

-0.53

yll

-0.52

ortions

-0.52

 alia

-0.52

 cong

-0.52

Promoting

-0.51

Quat

-0.51

POSITIVE LOGITS

 Decide

1.11

Decide

1.04

 decides

1.03

 decide

1.01

 decided

1.00

 DECISION

1.00

 Decided

0.99

 deciding

0.98

decide

0.88

 decision

0.87

Activations Density 0.176%

instances of the word "decided"

"decided"

deciding to do something

No Comments

No Known Activations