INDEX

Explanations

references to time, particularly the word "last" and its variants indicating recent events or periods

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

"Last" followed by a time period

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

bootstrapcdn

-0.46

rvore

-0.39

harusnya

-0.36

EXC

-0.36

 ilman

-0.35

 anuncios

-0.34

 Democrá

-0.34

msgTypes

-0.33

volmente

-0.33

 palvel

-0.32

POSITIVE LOGITS

 week

1.12

 year

1.09

 weekend

0.97

 month

0.96

 Saturday

0.83

 Monday

0.81

 Thursday

0.81

 Friday

0.79

 Tuesday

0.79

 Wednesday

0.79

Activations Density 0.050%

references to time, particularly the word "last" and its variants indicating recent events or periods

"Last" followed by a time period

No Comments

No Known Activations