INDEX

Explanations

the word "same" in various contexts, indicating a focus on similarities or sameness in descriptions or comparisons

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

"same"

np_acts-logits-general · gemini-2.0-flash

same as

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

AddTagHelper

-0.63

AndEndTag

-0.61

 thine

-0.52

principalTable

-0.51

Emer

-0.49

deauna

-0.49

ReusableCell

-0.47

 passim

-0.47



-0.46

 OnInit

-0.46

POSITIVE LOGITS

 same

1.35

same

1.30

Same

1.21

 mismo

1.07

 Same

1.06

 samma

1.06

 mesmos

1.03

 mismos

1.02

เดียว

0.99

 samme

0.99

Activations Density 0.276%

the word "same" in various contexts, indicating a focus on similarities or sameness in descriptions or comparisons

"same"

same as

No Comments

No Known Activations

the word "same" in various contexts, indicating a focus on similarities or sameness in descriptions or comparisons

"same"

same as

No Comments

No Known Activations