INDEX

Explanations

phrases related to critical situations or conflicts

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

upt

-0.69

aneously

-0.62

bj

-0.62

AMY

-0.62

photos

-0.60

nces

-0.60

ILY

-0.60

IUM

-0.59

anian

-0.58

istar

-0.57

POSITIVE LOGITS

 proverbial

0.84

 sleeve

0.69

 sleeves

0.67

 mouth

0.64

 roses

0.64

hat

0.64

 glove

0.63

 lettuce

0.61

 bisc

0.60

 riches

0.60

Activations Density 3.218%

phrases related to critical situations or conflicts

No Comments

No Known Activations