INDEX

Explanations

phrases related to a call to action or specific instructions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Show"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 hurd

-0.73

é¾įå¥ĳå£«

-0.67

 Dame

-0.61

 Bere

-0.59

Pes

-0.58

 Vengeance

-0.56

 Cologne

-0.55

kj

-0.54

ãĥ´

-0.54

 Raider

-0.53

POSITIVE LOGITS

 Thumbnails

0.86

isodes

0.70

iao

0.68

biz

0.67

Chart

0.66

hide

0.63

INGS

0.61

Cause

0.60

ing

0.60

tip

0.60

Activations Density 0.025%

phrases related to a call to action or specific instructions

instances of the word "Show"

No Comments

No Known Activations