INDEX

Explanations

references to processes and evaluations in scientific or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalTable

-0.96

sizeCache

-0.89

NameInMap

-0.84

ंदीखरीदारी

-0.75

 للمعارف

-0.71

 dAtA

-0.70

 SwitchCompat

-0.70

 ModelExpression

-0.70

 Réponses

-0.69

 سكانية

-0.68

POSITIVE LOGITS

is

1.49

has

1.43

was

1.36

 seems

1.36

 will

1.31

 adalah

1.24

 includes

1.24

 appears

1.21

 would

1.16

may

1.15

Activations Density 4.314%

references to processes and evaluations in scientific or legal contexts

No Comments

No Known Activations