INDEX

Explanations

the word "though" used in sentences

oai_token-act-pair · gpt-3.5-turbo

the word "though" and variations of its usage in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ursed

-0.73

ru

-0.68

rouse

-0.67

amed

-0.65

lees

-0.64

irs

-0.64

isible

-0.64

aven

-0.64

urized

-0.63

ask

-0.62

POSITIVE LOGITS

 acknowledging

0.79

 tradem

0.73

 admittedly

0.72

 conced

0.71

olicy

0.69

soever

0.68

CLASSIFIED

0.68

 moder

0.67

 recogn

0.66

 ideally

0.65

Activations Density 0.028%

the word "though" used in sentences

the word "though" and variations of its usage in context

No Comments

No Known Activations