INDEX

Explanations

references to prior events or conditions

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

"Prior" followed by a preposition

np_acts-logits-general · gemini-2.0-flash

prior to or past

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 later

-0.72

 później

-0.68

 pozdě

-0.63

 später

-0.62

 afterward

-0.62

 afterwards

-0.60

bbero

-0.60

 senere

-0.59

 kés

-0.59

 senare

-0.57

POSITIVE LOGITS

itisation

1.05

 generations

1.04

 experience

0.87

 iterations

0.81

 incar

0.79

 eras

0.78

 experiences

0.76

 incarnation

0.74

ArgsConstructor

0.74

StoryboardSegue

0.73

Activations Density 0.152%

references to prior events or conditions

"Prior" followed by a preposition

prior to or past

No Comments

No Known Activations