INDEX

Explanations

numeric data and measurements related to health or weight

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

Numbers within parentheses

np_acts-logits-general · gemini-2.0-flash

numbers within parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.73

-0.72

-0.71

-0.70

-0.69

-0.68

-0.66

<eos>

-0.66

↵

-0.65

↵↵

-0.65

POSITIVE LOGITS

Efq

1.38

 Савезне

1.37

 تضيفلها

1.30

 Monfieur

1.28

 الحره

1.25

 myſelf

1.25

IntoConstraints

1.25

 doubtnut

1.17

 resourceCulture

1.15

ſelf

1.15

Activations Density 0.850%

numeric data and measurements related to health or weight

Numbers within parentheses

numbers within parentheses

No Comments

No Known Activations