INDEX

Explanations

terms related to specific medical conditions and treatments

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

similar to "ran" or "gan"

np_acts-logits-general · gemini-2.0-flash

ran, tan, gan, fan words

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 protoimpl

-0.73

 Correia

-0.72

entreprises

-0.71

AddWithValue

-0.70

">//

-0.68

dhism

-0.68

NOPQRST

-0.67

riguez

-0.66

ViewStyle

-0.65

 getResource

-0.65

POSITIVE LOGITS

ran

0.92

zan

0.86

jan

0.81

fan

0.80

anan

0.78

lan

0.78

van

0.75

ZAN

0.75

Saman

0.74

ran

0.74

Activations Density 0.549%

terms related to specific medical conditions and treatments

similar to "ran" or "gan"

ran, tan, gan, fan words

No Comments

No Known Activations