INDEX

Explanations

phrases related to conflict or controversy

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

getLastName

-0.54

longValue

-0.50

getKeyCode

-0.48

isBlank

-0.47

openSession

-0.47

CurrentValue

-0.47

deleteById

-0.45

 Toilette

-0.45

getNombre

-0.44

isNotNull

-0.43

POSITIVE LOGITS

 élas

0.68

 unden

0.67

 compen

0.66

 remonte

0.65

 GETS

0.64

<bos>

0.63

 goû

0.63

 véhic

0.63

 imprimée

0.63

 getty

0.62

Activations Density 0.085%

phrases related to conflict or controversy

No Comments

No Known Activations