INDEX

Explanations

phrases within quotation marks

oai_token-act-pair · gpt-3.5-turbo

quoted phrases and statements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 rall

-0.81

rul

-0.80

 affiliate

-0.75

 Mehran

-0.73

 arri

-0.73

 nodd

-0.72

 matter

-0.71

 Story

-0.70

 tabl

-0.70

 Azerb

-0.70

POSITIVE LOGITS

every

1.27

their

1.24

ordinary

1.18

no

1.17

normal

1.14

false

1.14

almost

1.14

absolutely

1.13

moderate

1.12

someone

1.11

Activations Density 0.130%

phrases within quotation marks

quoted phrases and statements within the text

No Comments

No Known Activations