INDEX

Explanations

information related to news articles and press releases

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

 GeoNames

-0.79

Hvad

-0.73

Preço

-0.71

calciatore

-0.70

hdessä

-0.69

Flere

-0.69

 ***!

-0.68

GRANTED

-0.67

Eacute

-0.67

Dienstag

-0.66

POSITIVE LOGITS

 encomp

1.41

 accla

1.34

 depic

1.33

 intersper

1.33

 shenan

1.28

 maneu

1.27

 volunte

1.24

 reluct

1.22

 practition

1.21

 indestru

1.21

Activations Density 0.145%

information related to news articles and press releases

No Comments

No Known Activations