INDEX

Explanations

references to prior analysis or previously mentioned information 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ecuzione

-0.53

 thereunder

-0.52

SBATCH

-0.48

หนึ่ง

-0.48

numerusform

-0.48

Réponse

-0.48

llow

-0.48

RRect

-0.47

 Lorsqu

-0.47

 lont

-0.46

POSITIVE LOGITS

Referanser

0.67

 tadi

0.65

 discussed

0.65

 MonoBehaviour

0.62

 earlier

0.56

 précédents

0.55

 anteriores

0.55

 preceding

0.53

 talked

0.51

 previous

0.51

Activations Density 0.886%

references to prior analysis or previously mentioned information in the text

No Comments

No Known Activations