INDEX

Explanations

references to individuals involved in military incidents

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

Name followed by past tense "was/had"

np_acts-logits-general · gemini-2.0-flash

He/She/They had died

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

nestjs

-0.58

roveň

-0.50

tead

-0.49

 tiêu

-0.49

 actuels

-0.47

mybatisplus

-0.46

 thuyết

-0.46

inken

-0.46

 फिर

-0.46

sätzlich

-0.46

POSITIVE LOGITS

SharedDtor

0.75

ArrowToggle

0.71

Personensuche

0.68

 propOrder

0.67

 onCreateView

0.66

 Había

0.66

 kaynağından

0.64

SourceChecksum

0.64

cellation

0.64

CppMethod

0.63

Activations Density 0.149%

references to individuals involved in military incidents

Name followed by past tense "was/had"

He/She/They had died

No Comments

No Known Activations