INDEX

Explanations

phrases indicating superiority or excellence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the concept of "best" or superiority

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chy

-0.66

ngth

-0.65

idon

-0.63

 Emer

-0.62

cking

-0.61

kers

-0.61

ascade

-0.60

IGHTS

-0.59

 Reloaded

-0.59

kefeller

-0.58

POSITIVE LOGITS

seller

1.20

iary

1.09

sell

1.09

 suited

1.08

ow

1.08

owing

1.07

ows

1.07

iaries

1.06

ower

1.06

ial

0.94

Activations Density 0.051%

phrases indicating superiority or excellence

phrases indicating the concept of "best" or superiority

No Comments

No Known Activations