INDEX

Explanations

expressions of personal belief and agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 مشين

-0.83

تقاوى

-0.76

 <>",

-0.70

Datuak

-0.68

 שוליים

-0.62

 فريبيس

-0.57

LookAnd

-0.56

Билгалдахарш

-0.55

 تضيفلها

-0.54

SharedCtor

-0.53

POSITIVE LOGITS

 completely

2.36

 totally

2.02

 entirely

2.01

 Completely

1.98

completely

1.93

 fully

1.91

Completely

1.90

 COMPLE

1.73

 wholly

1.68

 completamente

1.68

Activations Density 0.507%

expressions of personal belief and agreement

No Comments

No Known Activations