INDEX

Explanations

internet domain names ending with ".net"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "net."

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

âĺħâĺħ

-0.70

sbm

-0.67

 Barcl

-0.64

=-=-=-=-

-0.64

HH

-0.61

FontSize

-0.61

 unres

-0.61

 Templar

-0.60

Topic

-0.59

=-=-=-=-=-=-=-=-

-0.59

POSITIVE LOGITS

anyahu

1.39

izens

1.36

izen

1.33

sov

1.11

working

1.10

works

1.03

aji

0.99

WORK

0.97

tering

0.96

ted

0.94

Activations Density 0.014%

internet domain names ending with ".net"

occurrences of the word "net."

No Comments

No Known Activations