INDEX

Explanations

phrases related to imparting a message of caution or 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 increa

-1.49

 milf

-1.48

 affor

-1.43

 alre

-1.38

fuf

-1.36

 madonna

-1.36

 perfet

-1.35

 disagre

-1.33

 scrat

-1.33

 strick

-1.32

POSITIVE LOGITS

testify

0.52

da

0.52

PerformLayout

0.51

FloatField

0.49

щадь

0.48

Até

0.48

how

0.48

BoxShadow

0.48

why

0.48

 też

0.47

Activations Density 0.337%

phrases related to imparting a message of caution or warning

No Comments

No Known Activations