INDEX

Explanations

instances where the protagonist takes action or demonstrates agency

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "I."

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

pires

-0.66

tains

-0.63

ãĥĬ

-0.62

INGTON

-0.60

groupon

-0.58

 Sterling

-0.58

 Emin

-0.58

 electromagnetic

-0.58

iston

-0.56

 Philipp

-0.56

POSITIVE LOGITS

'm

1.32

've

1.26

 suppose

1.16

 guess

1.05

'll

1.04

'd

1.03

 awoke

0.98

ggy

0.97

 presume

0.97

ulia

0.92

Activations Density 0.286%

instances where the protagonist takes action or demonstrates agency

instances of the pronoun "I."

No Comments

No Known Activations