INDEX

Explanations

phrases related to geographical locations, particularly islands and administrative divisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AutoSize

-0.52

...

-0.45

obe

-0.43

 onBind

-0.42

 remet

-0.42

 regole

-0.42

 popoli

-0.42

-0.41

enterOuterAlt

-0.41

 tradisional

-0.40

POSITIVE LOGITS

 ProtoMessage

0.94

Personendaten

0.91

########.

0.84

 itſelf

0.83

 AssemblyTitle

0.82

 greateſt

0.82

StructEnd

0.81

ſelf

0.79

 ſeveral

0.79

 Cayman

0.79

Activations Density 0.924%

phrases related to geographical locations, particularly islands and administrative divisions

No Comments

No Known Activations