INDEX

Explanations

attributes related to scientific discoveries and their implications

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

ThroughAttribute

-0.77

 houſe

-0.77

 Monfieur

-0.76

 themſelves

-0.76

 Majefty

-0.76

 itſelf

-0.74

 purpoſe

-0.74

 leaſt

-0.74

kuuta

-0.73

yntaxException

-0.73

POSITIVE LOGITS

"}")

0.64

0.63

0.58

++)

0.55

the

0.54

an

0.52

₂)

0.51

]')

0.51

 importance

0.50

')

0.50

Activations Density 0.548%

attributes related to scientific discoveries and their implications

No Comments

No Known Activations