INDEX

Explanations

terms and phrases related to legal or technical definitions

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

 panik

-0.78

 plak

-0.73

 adal

-0.72

 kask

-0.71

 torba

-0.70

 kaos

-0.70

 malin

-0.70

 kras

-0.69

 migli

-0.67

 interv

-0.66

POSITIVE LOGITS

0.83

“

0.78

0.76

‘

0.74

«

0.70

 ‘‘

0.68

 actionTypes

0.64

„

0.63

 Ename

0.63

``

0.63

Activations Density 0.163%

terms and phrases related to legal or technical definitions

No Comments

No Known Activations