INDEX

Explanations

instances of significant events or specific mentions in a narrative, particularly focusing on impactful statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

GEBURTSDATUM

-0.76

 فريبيس

-0.73

withIdentifier

-0.68

 tantum

-0.68

ArgsConstructor

-0.65

CWE

-0.65

 виправивши

-0.65

 ویکی‌پدیا

-0.65

PickerController

-0.62

الدراسه

-0.60

POSITIVE LOGITS

ValueStyle

0.67

 looked

0.61

PRNewswire

0.54

 looking

0.54

 DBNull

0.53

RUnlock

0.52

Looking

0.49

 stood

0.47

 nodded

0.47

 glared

0.47

Activations Density 0.112%

instances of significant events or specific mentions in a narrative, particularly focusing on impactful statements

No Comments

No Known Activations