INDEX

Explanations

phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

quotation marks and their contents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.74

 Nieto

-0.73

 Rica

-0.72

 upon

-0.68

 describ

-0.67

 jailed

-0.66

 relate

-0.64

 viewers

-0.63

 McGr

-0.63

 accompl

-0.62

POSITIVE LOGITS

most

1.26

official

1.25

classic

1.24

ultimate

1.16

little

1.12

original

1.09

Ultimate

1.08

best

1.08

problem

1.06

Golden

1.06

Activations Density 0.054%

phrases enclosed in quotation marks

quotation marks and their contents

No Comments

No Known Activations