INDEX

Explanations

phrases that indicate past actions or conditions

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

verwijspagina

-0.95

 itſelf

-0.80

URLException

-0.78

 Theſe

-0.73

visející

-0.71

 VizieR

-0.71

Hentet

-0.71

 recevez

-0.69

mybatisplus

-0.67

 تانيه

-0.67

POSITIVE LOGITS

 haber

0.64

</td>

0.59

had

0.52

Has

0.52

have

0.52

 viss

0.51

Has

0.51

"]:

0.50

sa

0.50

 hadn

0.49

Activations Density 0.174%

phrases that indicate past actions or conditions

No Comments

No Known Activations