INDEX

Explanations

information about organizations, locations, events, and other specific entities mentioned in documents or news articles

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

 vola

-0.70

hek

-0.67

 krab

-0.65

 toilette

-0.62

 quitt

-0.61

 marte

-0.61

 aquare

-0.59

 stiller

-0.59

zui

-0.57

 elek

-0.57

POSITIVE LOGITS

 maneu

0.81

 shenan

0.79

 depic

0.78

 sophistic

0.75

 stickied

0.72

 accla

0.72

 impra

0.70

 attemp

0.68

 upvoted

0.67

 resemb

0.67

Activations Density 0.872%

information about organizations, locations, events, and other specific entities mentioned in documents or news articles

No Comments

No Known Activations