INDEX

Explanations

phrases related to legal standards and protocols

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

standard deviation

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 AssemblyTitle

-0.88

WriteLiteral

-0.79

 שוליים

-0.69

+#+#

-0.68

 createState

-0.67

Efq

-0.67

RepeatedField

-0.66

 Conſ

-0.66

 Reſ

-0.66

PullParser

-0.65

POSITIVE LOGITS

 deviation

0.58

deviation

0.52

 Deviation

0.51

zed

0.49

Deviation

0.47

дон

0.47

 откло

0.47

 devi

0.47

 Chartered

0.46

 desvi

0.46

Activations Density 0.172%

phrases related to legal standards and protocols

standard deviation

No Comments

No Known Activations