INDEX

Explanations

phrases that indicate conditions or states related to "that"

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

enumi

-0.71

addPreferredGap

-0.54

 Trus

-0.51

پیوند

-0.49

ksy

-0.48

omation

-0.47

போ

-0.47

 huyền

-0.47

Осно

-0.47

UDO

-0.47

POSITIVE LOGITS

wherein

0.78

 sodass

0.77

Geplaatst

0.77

Хьажоргаш

0.73

 whereof

0.70

 wherein

0.69

kubectl

0.68

 înc

0.67

 whereby

0.64

 Jérusalem

0.63

Activations Density 0.279%

phrases that indicate conditions or states related to "that"

No Comments

No Known Activations