INDEX

Explanations

the word "given" and its context in relation to statements or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Normandy

-0.87

 Normandie

-0.76

 AppColors

-0.73

enumii

-0.70

effetto

-0.70

صرية

-0.70

 venons

-0.67

 tasche

-0.66

 Pamplona

-0.66

Unsubscribe

-0.66

POSITIVE LOGITS

 Given

1.29

 given

1.22

Given

1.16

given

1.07

iven

1.06

 GIVEN

0.98

Dado

0.96

 Dado

0.90

 dado

0.88

dado

0.86

Activations Density 0.136%

the word "given" and its context in relation to statements or claims

No Comments

No Known Activations