INDEX

Explanations

instances where the text mentions a comparison or evaluation between two different possibilities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating varying degrees of awareness or knowledge

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pony

-0.89

arks

-0.72

ETS

-0.68

 Siege

-0.66

oleon

-0.63

 Cipher

-0.63

 journals

-0.62

edia

-0.62

ocrats

-0.61

 Puzz

-0.61

POSITIVE LOGITS

chard

1.34

nam

1.29

acle

1.25

ifice

1.22

acles

1.20

Else

1.15

leans

1.13

acular

1.11

nery

1.09

ific

1.07

Activations Density 0.100%

instances where the text mentions a comparison or evaluation between two different possibilities

phrases indicating varying degrees of awareness or knowledge

No Comments

No Known Activations