INDEX

Explanations

references to political, governmental, and legislative topics

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

fitting

-0.70

appropriate

-0.68

soType

-0.61

taining

-0.60

-0.59

Fla

-0.58

 Durham

-0.57

cellaneous

-0.57

ORY

-0.56

irming

-0.56

POSITIVE LOGITS

 lacks

1.28

 cannot

1.19

 possesses

1.14

 lacked

1.13

 behaves

1.07

 tends

1.07

 suffers

1.04

 outper

1.03

 relies

1.03

 excel

1.03

Activations Density 0.501%

references to political, governmental, and legislative topics

No Comments

No Known Activations