INDEX

Explanations

phrases related to timing and the evaluation of statements or situations

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

 inconce

-1.47

 disagre

-1.46

 accla

-1.38

 unspeak

-1.37

 Intere

-1.37

 indescri

-1.34

 indestru

-1.33

 peppa

-1.32

 swarovski

-1.32

 reluct

-1.31

POSITIVE LOGITS

 anything

0.77

anything

0.74

 conclusions

0.69

 <<<<<<<<<<<<<<

0.68

Anything

0.66

any

0.66

렷

0.65

Personensuche

0.63

IsContent

0.63

Jeografia

0.62

Activations Density 0.245%

phrases related to timing and the evaluation of statements or situations

No Comments

No Known Activations