INDEX

Explanations

references to spending time and learning activities

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

"time" or a duration

np_acts-logits-general · gemini-2.0-flash

spending time on activities

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 GenerationType

-0.62

XmlAccessorType

-0.56

IntoConstraints

-0.52

 chrétien

-0.48

 grève

-0.44

 yık

-0.43

 opérés

-0.43

itzende

-0.42

 sinais

-0.42

 démar

-0.42

POSITIVE LOGITS

 devoted

0.62

 spent

0.60

 dedicado

0.59

 time

0.58

Time

0.55

TimeTo

0.55

 TIME

0.54

 updateTime

0.54

 dedicada

0.54

__":

0.53

Activations Density 0.138%

references to spending time and learning activities

"time" or a duration

spending time on activities

No Comments

No Known Activations