INDEX

Explanations

specific examples or instances of concepts, particularly in academic or technical contexts

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

Follows "example", "one", or "big"

np_acts-logits-general · gemini-2.0-flash

example of one

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

seamnă

-0.46

зен

-0.44

py

-0.43

uan

-0.42

 side

-0.42

finally

-0.42

py

-0.40

Use

-0.39

 statt

-0.39

uml

-0.39

POSITIVE LOGITS

 تضيفلها

0.96

 defStyleAttr

0.86

bewerken

0.81

ReusableCell

0.78

 Particularly

0.73

 antaranya

0.72

CloseOperation

0.70

 Baillargeon

0.68

脚注の使い方

0.68

 dabei

0.68

Activations Density 0.305%

specific examples or instances of concepts, particularly in academic or technical contexts

Follows "example", "one", or "big"

example of one

No Comments

No Known Activations