INDEX

Explanations

hexadecimal values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

TestingModule

-0.60

)"),

-0.59

 Vare

-0.59

存于互联网档案馆

-0.59

 numberOfRows

-0.58

 propOrder

-0.58

 mentales

-0.58

RepeatedField

-0.57

SES

-0.57

Half

-0.57

POSITIVE LOGITS

xff

3.51

xFF

2.55

XFF

1.52

xfe

1.24

xffff

1.21

xFFFF

1.11

xffffffff

1.08

xffffff

1.01

xFE

0.98

xFFFFFFFF

0.94

Activations Density 0.054%

hexadecimal values

No Comments

No Known Activations