INDEX

Explanations

references to jars

oai_token-act-pair · gpt-3.5-turbo

references to jars, particularly in the context of various uses and contents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Fighting

-0.72

ãģį

-0.71

 Proced

-0.67

enhagen

-0.67

 Hedge

-0.66

nesota

-0.65

opausal

-0.65

¶æ

-0.64

 Accountability

-0.64

 Reform

-0.63

POSITIVE LOGITS

jar

1.37

 jars

1.36

Jar

1.06

 flask

0.88

bling

0.87

jar

0.84

oon

0.83

bean

0.83

bles

0.81

Jar

0.81

Activations Density 0.009%

references to jars

references to jars, particularly in the context of various uses and contents

No Comments

No Known Activations