INDEX

Explanations

temporal expressions indicating durations or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Efq

-0.87

 /\.(

-0.86

 Jefus

-0.78

 fhew

-0.78

 pleaſure

-0.77

/>";

-0.75

makeConstraints

-0.74

ſelf

-0.73

 utafitiHapana

-0.72

 purpoſe

-0.72

POSITIVE LOGITS

ago

0.66

脚注の使い方

0.60

 before

0.54

 prior

0.54

 long

0.54

 earlier

0.52

먼

0.51

 years

0.48

 short

0.47

demment

0.47

Activations Density 0.104%

temporal expressions indicating durations or time periods

No Comments

No Known Activations