INDEX

Explanations

references to awards and honors

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

SequentialGroup

-0.83

 dejen

-0.69

="<?=

-0.69

ities

-0.68

pse

-0.66

']?>

-0.66

Nucle

-0.65

 Иль

-0.65

vann

-0.65

 "','

-0.64

POSITIVE LOGITS

 awards

1.77

 Awards

1.66

awards

1.55

 award

1.52

 AWARDS

1.50

 Award

1.49

 AWARD

1.49

Awards

1.45

Award

1.40

award

1.31

Activations Density 0.052%

references to awards and honors

No Comments

No Known Activations