INDEX

Explanations

phrases related to skepticism or disbelief

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

 Chapitre

-0.66

 Traité

-0.65

 quitt

-0.65

fta

-0.63

 Messieurs

-0.61

Takeaways

-0.60

 Lég

-0.60

 congr

-0.60

 véhic

-0.60

 fameux

-0.60

POSITIVE LOGITS

 rather

0.64

 aimed

0.53

 undertaken

0.49

internalType

0.49

 unworthy

0.48

awsze

0.46

 meant

0.46

0.45

 intended

0.45

 aiming

0.45

Activations Density 0.446%

phrases related to skepticism or disbelief

No Comments

No Known Activations