INDEX

Explanations

phrases related to warnings or alerts regarding system issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Unsc

-0.57

DockStyle

-0.57

 ISNI

-0.53

 undersigned

-0.51

THON

-0.51

transmitters

-0.50

 primaries

-0.49

 Petitioners

-0.48

tvguidetime

-0.48

Personendaten

-0.48

POSITIVE LOGITS

 message

1.46

 alert

1.40

 warning

1.35

 messages

1.26

alert

1.25

 Message

1.25

 Alert

1.23

message

1.22

Message

1.21

 notification

1.21

Activations Density 0.313%

phrases related to warnings or alerts regarding system issues

No Comments

No Known Activations