INDEX

Explanations

phrases related to events, particularly situations involving potential incidents or emergencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Toponymie

-0.54

 starved

-0.46

<tbody>

-0.45

ままで

-0.45

new

-0.42

 perception

-0.42

wpdb

-0.42

 palpable

-0.41

ICOLON

-0.40

󠁿

-0.40

POSITIVE LOGITS

 emergencies

0.97

 emergency

0.92

 contingencies

0.83

emergency

0.81

 Emer

0.76

 Emergency

0.74

 évent

0.73

 situations

0.72

gencies

0.72

万一

0.70

Activations Density 0.274%

phrases related to events, particularly situations involving potential incidents or emergencies

No Comments

No Known Activations