INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

instances of empty or irrelevant content

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

ÏĢ

-0.80

ceive

-0.74

ptr

-0.71

assed

-0.68

Â¯

-0.68

thood

-0.68

Ïī

-0.68

leen

-0.68

!.

-0.67

POSITIVE LOGITS

resa

1.45

odore

1.37

oret

1.33

 latter

1.15

 latest

1.10

ories

1.07

 biggest

0.98

 irony

0.95

 idea

0.94

 earliest

0.92

Activations Density 0.399%

proper nouns

instances of empty or irrelevant content

No Comments

No Known Activations