INDEX

Explanations

phrases or words indicating permanence or consistency

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

"always"

np_acts-logits-general · gemini-2.0-flash

always been

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 للمعارف

-0.70

RenderAtEndOf

-0.36

.*")]

-0.36

 teď

-0.35

ៗ

-0.35

 derzeit

-0.34

 poslední

-0.34

 vuoto

-0.34

 Inseln

-0.33

ukone

-0.33

POSITIVE LOGITS

 always

0.77

 Always

0.73

Always

0.71

always

0.70

 ALWAYS

0.65

 Siempre

0.58

我一直

0.58

昔から

0.56

Siempre

0.56

一直

0.56

Activations Density 0.173%

phrases or words indicating permanence or consistency

"always"

always been

No Comments

No Known Activations