INDEX

Explanations

medical terms related to health conditions and treatments

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

Tokens preceding phrases in parentheses

np_acts-logits-general · gemini-2.0-flash

introducing alternative names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 myſelf

-1.31

 itſelf

-1.28

 Anſ

-1.14

 raiſ

-1.10

 chofe

-1.09

 doubtnut

-1.09

 Jefus

-1.07

 himſelf

-1.07

 Monfieur

-1.05

 themſelves

-1.05

POSITIVE LOGITS

1.21

‘

1.21

“

1.18

1.15

 sogenannten

0.99

«

0.98

0.93

 sogenannte

0.89

„

0.87

tzw

0.81

Activations Density 0.813%

medical terms related to health conditions and treatments

Tokens preceding phrases in parentheses

introducing alternative names

No Comments

No Known Activations