INDEX

Explanations

phrases related to emphasizing a point or reacting to a statement

oai_token-act-pair · gpt-3.5-turbo

phrases or expressions that convey a sense of disbelief or surprise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iatric

-0.79

oreal

-0.73

iliated

-0.73

ieg

-0.72

oufl

-0.71

strate

-0.70

ettel

-0.68

Contents

-0.68

ivil

-0.67

éĸ

-0.67

POSITIVE LOGITS

!:

0.79

Kev

0.77

 yourselves

0.72

 Suns

0.67

 Cory

0.66

 analogy

0.63

Sco

0.62

!'"

0.61

 Cohn

0.60

 Krish

0.60

Activations Density 0.169%

phrases related to emphasizing a point or reacting to a statement

phrases or expressions that convey a sense of disbelief or surprise

No Comments

No Known Activations