INDEX

Explanations

references to specific medical conditions and terms related to health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

↵↵

-0.84

-0.70

-0.69

enumi

-0.66

-0.65

-0.64

-0.63

__()

-0.63

...

-0.63

-0.60

POSITIVE LOGITS

 autorytatywna

0.81

verifyException

0.80

 betweenstory

0.78

 itſelf

0.74

RegistryLite

0.74

 ddelweddau

0.74

TintMode

0.73

DIPSETTING

0.73

Šaltiniai

0.72

帖最后由

0.72

Activations Density 0.254%

references to specific medical conditions and terms related to health

No Comments

No Known Activations