INDEX

Explanations

references to actions and commands involving "we," "I," and forms of "to let."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 TextAppearance

-0.53

 HttpResponse

-0.52

 aidant

-0.51

 connexe

-0.50

lah

-0.49

 Rine

-0.47

OGND

-0.47

LabelTagHelper

-0.46

 boîte

-0.45

LElement

-0.44

POSITIVE LOGITS

Теперь

0.74

 continúas

0.71

 Теперь

0.71

ValueStyle

0.70

 autorytatywna

0.69

adaptiveStyles

0.67

ViewFeatures

0.67

RTSC

0.65

הערות

0.64

Maintenant

0.63

Activations Density 0.185%

references to actions and commands involving "we," "I," and forms of "to let."

No Comments

No Known Activations