INDEX

Explanations

references to objects or features related to tools or devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 hans

-0.46

-0.42

"""

-0.41

การ

-0.40

“

-0.38

'''

-0.38

↵↵

-0.38

ys

-0.38

"""

-0.38

POSITIVE LOGITS

RegressionTest

1.07

neath

0.93

تقاوى

0.92

 Paglinawan

0.91

+#+#

0.86

expandindo

0.85

 BorderRadius

0.82

StoryboardSegue

0.81

ftagPool

0.81

 entrambi

0.80

Activations Density 0.472%

references to objects or features related to tools or devices

No Comments

No Known Activations