INDEX

Explanations

occurrences of the phrase "of the."

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.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

ĸļ

-0.67

ovember

-0.64

Ã©e

-0.64

ahime

-0.63

atto

-0.62

heses

-0.60

=]

-0.60

 eliminates

-0.59

urated

-0.59

metics

-0.58

POSITIVE LOGITS

odor

0.78

tering

0.67

terness

0.63

 younger

0.63

older

0.62

effic

0.60

 these

0.60

 those

0.60

 older

0.60

arching

0.58

Activations Density 0.499%

occurrences of the phrase "of the."

No Comments

No Known Activations