INDEX

Explanations

references to the "Daily" publication or the concept of "daily" occurrences and goals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

transQ

-0.82

 progesterone

-0.79

 fraude

-0.75

iyaki

-0.75

 ovale

-0.74

 оригіналу

-0.72

ONYMOUS

-0.71

 trachea

-0.71

 Vorsitzender

-0.70

 Catholicism

-0.70

POSITIVE LOGITS

 Daily

2.07

Daily

1.98

daily

1.92

 daily

1.90

 DAILY

1.79

DAILY

1.67

 dagelijks

1.20

 täglichen

1.12

 codzien

1.05

 täglich

1.01

Activations Density 0.054%

references to the "Daily" publication or the concept of "daily" occurrences and goals

No Comments

No Known Activations