INDEX

Explanations

medical terminology related to examinations and percentages

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

“

-0.65

-0.59

-0.58

‘

-0.58

des

-0.55

 trans

-0.55

at

-0.55

-0.52

-0.51

POSITIVE LOGITS

Efq

1.35

 Majefty

1.28

 Monfieur

1.23

 Theſe

1.13

ſelves

1.13

 itſelf

1.10

 Jefus

1.10

ſelf

1.10

 Reſ

1.10

 myſelf

1.08

Activations Density 0.284%

medical terminology related to examinations and percentages

No Comments

No Known Activations