INDEX

Explanations

words related to toxic substances or chemical reactions

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 truce

-0.70

 fries

-0.67

 relativity

-0.64

ETHOD

-0.64

 permission

-0.64

Â¢

-0.64

FTWARE

-0.64

 quarters

-0.63

aiden

-0.61

kson

-0.61

POSITIVE LOGITS

imity

1.11

es

1.01

 Machina

0.96

peria

0.95

eus

0.94

iao

0.94

idation

0.92

edo

0.92

nard

0.89

uala

0.87

Activations Density 0.018%

words related to toxic substances or chemical reactions

No Comments

No Known Activations