INDEX

Explanations

mentions of plots or graphical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 preventiva

-0.50

fhir

-0.49

 Roskov

-0.49

abord

-0.49

 Warzone

-0.49

 TestBed

-0.49

中最

-0.48

ঞ

-0.47

 nedenle

-0.47

начала

-0.46

POSITIVE LOGITS

 Touch

1.20

 touch

1.12

 TOUCH

1.11

 kiss

1.06

hug

1.03

touch

0.99

kiss

0.98

 kissed

0.98

 Plot

0.97

Touch

0.97

Activations Density 0.255%

mentions of plots or graphical representations

No Comments

No Known Activations