INDEX

Explanations

mentions of the letter "R."

oai_token-act-pair · gpt-3.5-turbo

the presence of the letter "R" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

terson

-0.67

 Garmin

-0.65

 quantity

-0.64

CPR

-0.63

creen

-0.63

 Pose

-0.62

 Totem

-0.62

 Parenthood

-0.61

 Corpus

-0.61

 Nieto

-0.61

POSITIVE LOGITS

ansom

1.33

haps

1.31

outine

1.30

ascal

1.24

senal

1.22

ifles

1.21

otten

1.20

ushing

1.19

azz

1.15

attle

1.14

Activations Density 0.042%

mentions of the letter "R."

the presence of the letter "R" in various contexts

No Comments

No Known Activations