INDEX

Explanations

words related to conflict, especially in political or social contexts

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

OGND

-0.47

Gill

-0.46

Πηγές

-0.45

Père

-0.43

 handels

-0.43

Cuer

-0.43

wavering

-0.42

 Gill

-0.42

mvn

-0.41

CppMethod

-0.41

POSITIVE LOGITS

 conf

1.31

 Conf

1.22

 CONF

1.15

conf

1.12

Conf

1.08

CONF

0.95

 Confession

0.84

 Confessions

0.82

 confessions

0.73

 confeder

0.72

Activations Density 0.080%

words related to conflict, especially in political or social contexts

No Comments

No Known Activations