INDEX

Explanations

contractions of words, especially with a negative connotation or related to warning

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

 Traité

-0.72

mef

-0.68

 Secrétaire

-0.68

fup

-0.63

 sophie

-0.61

 Ministre

-0.61

fta

-0.61

 wien

-0.60

aen

-0.59

 Chapitre

-0.59

POSITIVE LOGITS

expandindo

0.71

<bos>

0.59

كويكب

0.52

stagland

0.51

 Belén

0.50

 Cáceres

0.49

fortawesome

0.49

 withRouter

0.48

 itemName

0.48

 kyllä

0.47

Activations Density 0.226%

contractions of words, especially with a negative connotation or related to warning

No Comments

No Known Activations