INDEX

Explanations

instances of closed, shut, or hidden expressions and concepts

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

↵

-0.43

程

-0.40

 Aufstieg

-0.40

-0.39

vs

-0.38

rem

-0.38

 revis

-0.37

天下

-0.37

 sortant

-0.36

POSITIVE LOGITS

extAlignment

1.00

 Roskov

0.98

 الاطلاع

0.97

 silence

0.94

ReusableCell

0.90

 Wikimedijinoj

0.88

 blind

0.87

AndEndTag

0.87

 TextAppearance

0.83

UIControlState

0.82

Activations Density 0.552%

instances of closed, shut, or hidden expressions and concepts

No Comments

No Known Activations