INDEX

Explanations

instructions or warnings related to physical objects, tools, or devices

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

 alkoh

-0.85

 pecuni

-0.84

 konserv

-0.79

 Áng

-0.79

 manuten

-0.79

 praktik

-0.78

capulco

-0.76

 radikal

-0.74

 inol

-0.74

 kalori

-0.74

POSITIVE LOGITS

the

1.06

 your

0.73

the

0.72

 MATHEMATICAL

0.67

 each

0.65

 OBSERVATIONS

0.63

its

0.61

THE

0.60

 PLATES

0.59

 EXERCISES

0.59

Activations Density 0.540%

instructions or warnings related to physical objects, tools, or devices

No Comments

No Known Activations