INDEX

Explanations

medical terms and research methodology related to clinical trials

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

 disagre

-1.62

 embodi

-1.58

 emphat

-1.56

 reluct

-1.54

 uncin

-1.52

 affor

-1.50

 squa

-1.50

 increa

-1.50

 perfon

-1.49

 suscep

-1.48

POSITIVE LOGITS

 Then

1.02

 They

0.92

 When

0.91

But

0.90

 While

0.89

 However

0.88

It

0.87

 That

0.87

 ***!

0.86

 After

0.85

Activations Density 0.476%

medical terms and research methodology related to clinical trials

No Comments

No Known Activations