INDEX

Explanations

phrases related to instructions or steps in a procedure

oai_token-act-pair · gpt-3.5-turbo

instances of the word "you."

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

 Notting

-0.72

 airs

-0.68

 Political

-0.68

 Scarborough

-0.68

Roz

-0.68

 Richmond

-0.67

 Pastor

-0.64

 Pulitzer

-0.64

Lago

-0.64

acular

-0.63

POSITIVE LOGITS

're

1.40

'll

1.21

've

1.20

 guessed

1.05

hei

1.03

'd

1.00

 encount

0.95

 know

0.95

 decide

0.93

 intend

0.93

Activations Density 0.216%

phrases related to instructions or steps in a procedure

instances of the word "you."

No Comments

No Known Activations