INDEX

Explanations

references to a specific character or TV show, "SpongeBob SquarePants."

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

 karbon

-0.69

 silikon

-0.67

 maksi

-0.64

 المعيارى

-0.63

 hunde

-0.61

 akut

-0.59

 akku

-0.58

uhr

-0.58

 nawr

-0.58

onViewCreated

-0.56

POSITIVE LOGITS

 indestru

0.79

 anthrop

0.64

 royaume

0.63

 adorable

0.59

 Nickelodeon

0.57

 cute

0.56

 mischievous

0.56

 kinderg

0.55

 Kindergarten

0.55

 cartoons

0.55

Activations Density 0.870%

references to a specific character or TV show, "SpongeBob SquarePants."

No Comments

No Known Activations