INDEX

Explanations

questions starting with the word "Why"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Why" indicating questions or inquiries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ICT

-0.79

est

-0.67

 prelim

-0.62

 sweep

-0.61

 possession

-0.61

 caps

-0.60

 touch

-0.60

 close

-0.59

 medium

-0.59

 delivery

-0.58

POSITIVE LOGITS

Why

3.02

Why

2.36

why

2.31

WHY

2.20

why

1.96

How

1.74

 What

1.61

 Reasons

1.56

 Wouldn

1.50

Isn

1.43

Activations Density 0.019%

questions starting with the word "Why"

instances of the word "Why" indicating questions or inquiries

No Comments

No Known Activations