INDEX

Explanations

the presence of the word "de," indicating a focus on its significance in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

DEL

-0.74

 Italijani

-0.69

MENAFN

-0.68

 ProtoMessage

-0.68

 disambiguazione

-0.63

 Theſe

-0.63

DEL

-0.62

Autoritní

-0.61

deli

-0.57

 éter

-0.57

POSITIVE LOGITS

de

1.28

den

0.75

lin

0.69

/**

0.68

def

0.65

UnsafeEnabled

0.64

Lin

0.63

 victoire

0.60

makeText

0.56

stens

0.55

Activations Density 0.124%

the presence of the word "de," indicating a focus on its significance in the text

No Comments

No Known Activations