INDEX

Explanations

acknowledgments and expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

יוחד

-0.49

reds

-0.47

tso

-0.45

ENARIO

-0.45

付け

-0.44

dymyr

-0.44

ÍST

-0.44

arthed

-0.43

ensed

-0.42

ใคร

-0.42

POSITIVE LOGITS

 being

1.25

being

1.10

 having

1.06

having

1.02

 étant

1.01

Being

0.96

 haberse

0.92

 habiendo

0.90

 esser

0.89

 BEING

0.88

Activations Density 0.174%

acknowledgments and expressions of gratitude

No Comments

No Known Activations