INDEX

Explanations

repeated references to a variable labeled "total."

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

|}{\

-0.64

utnik

-0.64

 jsPsych

-0.60

__(/*!

-0.60

<caption>

-0.60

 références

-0.59

}$}

-0.59

]$}

-0.59

 useAppContext

-0.59

PYX

-0.58

POSITIVE LOGITS

횟

0.77

Personendaten

0.65

 Kalt

0.60

getCount

0.58

 Voulez

0.57

Count

0.57

 myſelf

0.56

GIVEREF

0.55

 theſe

0.55

 ſeveral

0.54

Activations Density 0.102%

repeated references to a variable labeled "total."

No Comments

No Known Activations