INDEX

Explanations

phrases indicating sequential events or timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RectangleBorder

-0.70

gjenge

-0.61

 vectorielles

-0.58

 للمعارف

-0.57

 ouvertes

-0.57

cuerdo

-0.57

ftagPool

-0.57

новништво

-0.57

PhysRevD

-0.55

 extérieurs

-0.54

POSITIVE LOGITS

 thereafter

1.15

 Thereafter

1.00

 afterwards

0.96

 subsequent

0.94

 Danach

0.94

 danach

0.90

 subsequently

0.90

 onwards

0.86

 Daarna

0.85

以降

0.82

Activations Density 0.296%

phrases indicating sequential events or timelines

No Comments

No Known Activations