INDEX

Explanations

references to specific instances or occurrences related to time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

TIM

-0.81

 Timing

-0.79

 Timeline

-0.77

Timeline

-0.76

 Hours

-0.73

TIM

-0.72

Hours

-0.71

Timing

-0.68

apunov

-0.65

 Temporal

-0.64

POSITIVE LOGITS

 time

1.80

vez

1.00

 tijd

0.85

 fois

0.70

 время

0.68

 keer

0.66

 gång

0.64

time

0.64

 waktu

0.61

 čas

0.56

Activations Density 0.341%

references to specific instances or occurrences related to time

No Comments

No Known Activations