INDEX

Explanations

phrases related to physical attributes and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Rè

-0.66

Datuak

-0.64

libft

-0.64

ſelf

-0.64

BPI

-0.64

Lp

-0.61

-0.60

ParallelGroup

-0.60

 Jiří

-0.59

\]

-0.59

POSITIVE LOGITS

the

0.74

+#+#

0.68

 each

0.66

 every

0.61

 them

0.61

our

0.60

his

0.59

 فريبيس

0.59

 your

0.59

it

0.58

Activations Density 0.554%

phrases related to physical attributes and measurements

No Comments

No Known Activations