INDEX

Explanations

locations or potential future locations mentioned in a text

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

 Île

-0.52

Enumer

-0.52

$*$

-0.50

Semoga

-0.49

mydb

-0.48

Chk

-0.47

Ancho

-0.47

Nina

-0.47

mocked

-0.47

 marquer

-0.46

POSITIVE LOGITS

 destination

1.38

 destinations

1.35

 Destination

1.28

 Destinations

1.27

destination

1.18

Destination

1.12

destinations

0.93

 dest

0.90

 DEST

0.88

Destinations

0.88

Activations Density 0.075%

locations or potential future locations mentioned in a text

No Comments

No Known Activations