INDEX

Explanations

terms related to military actions and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enumi

-0.66

 تضيفلها

-0.65

verwijspagina

-0.58

CopyWith

-0.58

isement

-0.56

\{\\

-0.55

Personendaten

-0.55

 ligiloj

-0.53

CppMethod

-0.52

 يتيمه

-0.52

POSITIVE LOGITS

 attack

1.09

 invasion

1.01

 raid

0.96

 attacking

0.96

 Attack

0.96

 raids

0.95

 attacked

0.94

 attacks

0.93

 raided

0.93

 assault

0.93

Activations Density 0.388%

terms related to military actions and operations

No Comments

No Known Activations