INDEX

Explanations

references to healthcare and medical contexts

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

Code, math, or technical symbols

np_acts-logits-general · gemini-2.0-flash

exciting thing

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

().__

-0.54

mo

-0.52

ha

-0.52

Max

-0.52

Min

-0.50

bio

-0.48

min

-0.48

mi

-0.47

er

-0.47

th

-0.46

POSITIVE LOGITS

 myſelf

1.03

 Majefty

0.99

 themſelves

0.99

 itſelf

0.98

 Monfieur

0.94

 ainfi

0.90

 himſelf

0.89

 Jefus

0.89

 uſe

0.88

Efq

0.88

Activations Density 0.469%

references to healthcare and medical contexts

Code, math, or technical symbols

exciting thing

No Comments

No Known Activations