INDEX

Explanations

prepositional phrases indicating purpose or intended use

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

 mikina

-0.73

 Mercan

-0.71

XJ

-0.70

 Jacobi

-0.68

 Venetian

-0.68

Sche

-0.68

 dieß

-0.68

("'"

-0.67

..\..\

-0.67

ഘ

-0.66

POSITIVE LOGITS

for

1.78

FOR

1.72

For

1.55

for

1.55

FOR

1.50

For

1.45

 für

1.29

 voor

1.22

 για

1.16

 для

1.10

Activations Density 0.531%

prepositional phrases indicating purpose or intended use

No Comments

No Known Activations