INDEX

Explanations

terms related to military operations and investigations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mlle

-1.36

 disagre

-1.31

 intersper

-1.31

 increa

-1.29

 inev

-1.28

 guarante

-1.26

 snoopy

-1.26

 shenan

-1.26

 swarovski

-1.25

 affor

-1.24

POSITIVE LOGITS

QMetaType

0.56

xase

0.53

ModelSerializer

0.50

formik

0.49

keyColumn

0.48

thenReturn

0.47

IsContent

0.47

».

0.46

enderror

0.46

ModelAdmin

0.46

Activations Density 3.615%

terms related to military operations and investigations

No Comments

No Known Activations