INDEX

Explanations

scientific research-related terms and information

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

làm

-0.75

Đối

-0.71

Bảo

-0.68

Chỉ

-0.67

Đặc

-0.67

DisplayMetrics

-0.65

cần

-0.64

Làm

-0.63

Thể

-0.61

Trọng

-0.61

POSITIVE LOGITS

 maneu

1.51

 apprehen

1.44

 shenan

1.41

 hairc

1.41

 considér

1.41

 depic

1.40

 fameux

1.39

 impra

1.38

 unve

1.38

 milf

1.37

Activations Density 0.632%

scientific research-related terms and information

No Comments

No Known Activations