INDEX

Explanations

phrases indicating a connection, comparison, or alternation

oai_token-act-pair · gpt-3.5-turbo

conditional phrases expressing possibility or likelihood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Pony

-0.89

Cth

-0.88

 mummy

-0.65

 pandemonium

-0.61

 Steel

-0.60

 Centauri

-0.60

 Rocket

-0.60

 Columb

-0.59

 Chow

-0.58

 Rainbow

-0.58

POSITIVE LOGITS

acles

1.38

acular

1.26

chard

1.25

acle

1.24

leans

1.15

GAN

1.15

chid

1.12

Else

1.10

nery

1.08

lando

1.02

Activations Density 0.074%

phrases indicating a connection, comparison, or alternation

conditional phrases expressing possibility or likelihood

No Comments

No Known Activations