INDEX

Explanations

terms related to sharpness or precision

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 }}"></

-1.12

AndEndTag

-1.03

 arşivlendi

-1.01

SharedDtor

-1.01

+:+

-1.00

RenderAtEndOf

-0.93

Бахар

-0.92

$_"

-0.91

पया

-0.90

₁)

-0.90

POSITIVE LOGITS

 sharp

0.54

鋒

0.54

0.53

 adjacent

0.52

锋

0.51

0.49

0.48

 fant

0.47

↵↵

0.47

Activations Density 0.082%

terms related to sharpness or precision

No Comments

No Known Activations