INDEX

Explanations

references to time and duration

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

time, duration, and length

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 EconPapers

-0.51

 BoxDecoration

-0.46

 neutre

-0.42

ground

-0.42

 bağ

-0.41

ayuno

-0.40

 ground

-0.40

gemeins

-0.39

oose

-0.39

 grond

-0.39

POSITIVE LOGITS

 duration

0.81

Time

0.76

 Time

0.71

 time

0.71

Duration

0.67

 TIME

0.67

 updateTime

0.66

时长

0.66

time

0.65

 length

0.65

Activations Density 0.040%

references to time and duration

time, duration, and length

No Comments

No Known Activations